Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 117 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.3115. Min Act: -0.1700
Data Index: 1087299 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.2490. Min Act: -0.1700
Data Index: 3459570 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.2490. Min Act: -0.1700
Data Index: 5507923 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.2177. Min Act: -0.1700
Data Index: 708477 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.1552. Min Act: -0.1700
Data Index: 3922746 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.1240. Min Act: -0.1700
Data Index: 3577153 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.0927. Min Act: -0.1700
Data Index: 2791483 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.0614. Min Act: -0.1700
Data Index: 6580754 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.0614. Min Act: -0.1700
Data Index: 4207735 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.0614. Min Act: -0.1700
Data Index: 3559245 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.0302. Min Act: -0.1700
Data Index: 3222309 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.0302. Min Act: -0.1700
Data Index: 7713409 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3115. Min Range: -4.3115
Max Act: 4.0302. Min Act: -0.1700
Data Index: 6023554 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3115. Min Range: -4.3115
Max Act: 3.9989. Min Act: -0.1700
Data Index: 3813871 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3115. Min Range: -4.3115
Max Act: 3.9989. Min Act: -0.1700
Data Index: 4437894 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3115. Min Range: -4.3115
Max Act: 3.9989. Min Act: -0.1700
Data Index: 1986448 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3115. Min Range: -4.3115
Max Act: 3.9677. Min Act: -0.1700
Data Index: 669183 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3115. Min Range: -4.3115
Max Act: 3.9677. Min Act: -0.1700
Data Index: 722020 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3115. Min Range: -4.3115
Max Act: 3.9677. Min Act: -0.1700
Data Index: 3096397 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3115. Min Range: -4.3115
Max Act: 3.9677. Min Act: -0.1700
Data Index: 766255 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19