Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.8243. Min Act: -0.1700
Data Index: 5029644 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.6681. Min Act: -0.1700
Data Index: 6597503 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.5743. Min Act: -0.1700
Data Index: 306001 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.5431. Min Act: -0.1700
Data Index: 6537902 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.5431. Min Act: -0.1700
Data Index: 6253360 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.5118. Min Act: -0.1700
Data Index: 4509817 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.4806. Min Act: -0.1700
Data Index: 7071098 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.4806. Min Act: -0.1700
Data Index: 2944013 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.4806. Min Act: -0.1700
Data Index: 341451 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.4181. Min Act: -0.1700
Data Index: 316556 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.4181. Min Act: -0.1700
Data Index: 945042 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.3868. Min Act: -0.1700
Data Index: 122112 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.4181. Min Act: -0.1700
Data Index: 945043 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.3868. Min Act: -0.1700
Data Index: 7982664 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.3868. Min Act: -0.1700
Data Index: 3864243 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.3868. Min Act: -0.1700
Data Index: 1481838 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.3243. Min Act: -0.1700
Data Index: 4750073 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.2931. Min Act: -0.1700
Data Index: 432239 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.2618. Min Act: -0.1700
Data Index: 4086783 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.2306. Min Act: -0.1700
Data Index: 8139275 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19