< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 61 in Layer 43

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.8782. Min Act: -0.1700

Data Index: 1589799 (Open Web Text)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.6595. Min Act: -0.1700

Data Index: 1423332 (Open Web Text)

Max Activating Token Index: 451

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.5032. Min Act: -0.1700

Data Index: 4857485 (Open Web Text)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.4720. Min Act: -0.1700

Data Index: 6815360 (Open Web Text)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.4407. Min Act: -0.1700

Data Index: 2229679 (Open Web Text)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.4407. Min Act: -0.1700

Data Index: 5360953 (Open Web Text)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.3782. Min Act: -0.1700

Data Index: 5820275 (Open Web Text)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.3470. Min Act: -0.1700

Data Index: 7713139 (Open Web Text)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.3157. Min Act: -0.1700

Data Index: 2298253 (Open Web Text)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.3157. Min Act: -0.1700

Data Index: 8458981 (Open Web Text)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.2532. Min Act: -0.1700

Data Index: 6834059 (Open Web Text)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.2532. Min Act: -0.1700

Data Index: 4490152 (Open Web Text)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.2220. Min Act: -0.1700

Data Index: 6938890 (Open Web Text)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.2220. Min Act: -0.1700

Data Index: 1635403 (Open Web Text)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.1907. Min Act: -0.1700

Data Index: 5880867 (Open Web Text)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.1907. Min Act: -0.1700

Data Index: 1012991 (Open Web Text)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.1907. Min Act: -0.1700

Data Index: 2702597 (Open Web Text)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.1595. Min Act: -0.1700

Data Index: 3089905 (Open Web Text)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.1595. Min Act: -0.1700

Data Index: 6502404 (Open Web Text)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 7.8782. Min Range: -7.8782

Max Act: 7.1595. Min Act: -0.1700

Data Index: 4905271 (Open Web Text)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #19