< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6357 in Layer 40

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.9297. Min Act: -0.1700

Data Index: 8319542 (Open Web Text)

Max Activating Token Index: 280

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.8672. Min Act: -0.1700

Data Index: 1293133 (Open Web Text)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.8047. Min Act: -0.1700

Data Index: 5975535 (Open Web Text)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.7422. Min Act: -0.1700

Data Index: 7789583 (Open Web Text)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.7422. Min Act: -0.1700

Data Index: 1154973 (Open Web Text)

Max Activating Token Index: 482

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.7422. Min Act: -0.1700

Data Index: 1205746 (Open Web Text)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.6797. Min Act: -0.1700

Data Index: 4289663 (Open Web Text)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.6172. Min Act: -0.1700

Data Index: 6971172 (Open Web Text)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.6172. Min Act: -0.1700

Data Index: 663024 (Open Web Text)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.5547. Min Act: -0.1700

Data Index: 1340461 (Open Web Text)

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.5547. Min Act: -0.1700

Data Index: 5413770 (Open Web Text)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.5547. Min Act: -0.1700

Data Index: 3296643 (Open Web Text)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.5547. Min Act: -0.1700

Data Index: 5777967 (Open Web Text)

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.5547. Min Act: -0.1700

Data Index: 1164276 (Open Web Text)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.4922. Min Act: -0.1700

Data Index: 5050400 (Open Web Text)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.4922. Min Act: -0.1700

Data Index: 881362 (Open Web Text)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.4922. Min Act: -0.1700

Data Index: 2298077 (Open Web Text)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.4922. Min Act: -0.1700

Data Index: 6912003 (Open Web Text)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.4297. Min Act: -0.1700

Data Index: 1745535 (Open Web Text)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.9297. Min Range: -10.9297

Max Act: 10.4297. Min Act: -0.1700

Data Index: 1633513 (Open Web Text)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #19