< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6349 in Layer 31

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.5134. Min Range: -5.5134

Max Act: 5.5134. Min Act: -0.1700

Data Index: 5087369 (Open Web Text)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.5134. Min Range: -5.5134

Max Act: 5.4196. Min Act: -0.1700

Data Index: 5793169 (Open Web Text)

Max Activating Token Index: 346

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.5134. Min Range: -5.5134

Max Act: 5.3571. Min Act: -0.1700

Data Index: 3334717 (Open Web Text)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.5134. Min Range: -5.5134

Max Act: 5.1696. Min Act: -0.1700

Data Index: 8392320 (Open Web Text)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.5134. Min Range: -5.5134

Max Act: 5.1071. Min Act: -0.1700

Data Index: 1327211 (Open Web Text)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.5134. Min Range: -5.5134

Max Act: 5.1071. Min Act: -0.1700

Data Index: 4227348 (Open Web Text)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.5134. Min Range: -5.5134

Max Act: 5.0446. Min Act: -0.1700

Data Index: 6455584 (Open Web Text)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.5134. Min Range: -5.5134

Max Act: 5.0134. Min Act: -0.1700

Data Index: 980463 (Open Web Text)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.5134. Min Range: -5.5134

Max Act: 5.0134. Min Act: -0.1700

Data Index: 2218312 (Open Web Text)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.5134. Min Range: -5.5134

Max Act: 4.9509. Min Act: -0.1700

Data Index: 1065320 (Open Web Text)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.5134. Min Range: -5.5134

Max Act: 4.9196. Min Act: -0.1700

Data Index: 8440991 (Open Web Text)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.5134. Min Range: -5.5134

Max Act: 4.9196. Min Act: -0.1700

Data Index: 8438772 (Open Web Text)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.5134. Min Range: -5.5134

Max Act: 4.8259. Min Act: -0.1700

Data Index: 4136908 (Open Web Text)

Max Activating Token Index: 479

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.5134. Min Range: -5.5134

Max Act: 4.7946. Min Act: -0.1700

Data Index: 4684587 (Open Web Text)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.5134. Min Range: -5.5134

Max Act: 4.7946. Min Act: -0.1700

Data Index: 5207658 (Open Web Text)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.5134. Min Range: -5.5134

Max Act: 4.7634. Min Act: -0.1700

Data Index: 2824637 (Open Web Text)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.5134. Min Range: -5.5134

Max Act: 4.7634. Min Act: -0.1700

Data Index: 4656654 (Open Web Text)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.5134. Min Range: -5.5134

Max Act: 4.7321. Min Act: -0.1700

Data Index: 8303563 (Open Web Text)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.5134. Min Range: -5.5134

Max Act: 4.7321. Min Act: -0.1700

Data Index: 8406401 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.5134. Min Range: -5.5134

Max Act: 4.7321. Min Act: -0.1700

Data Index: 3284277 (Open Web Text)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #19