Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.9231. Min Act: -0.1700
Data Index: 5285535 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.9231. Min Act: -0.1700
Data Index: 7698288 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8919. Min Act: -0.1700
Data Index: 865093 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.6886. Min Act: -0.1700
Data Index: 4094819 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.6729. Min Act: -0.1700
Data Index: 913028 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.6729. Min Act: -0.1700
Data Index: 4625075 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5947. Min Act: -0.1700
Data Index: 3695499 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.6103. Min Act: -0.1700
Data Index: 1603467 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5634. Min Act: -0.1700
Data Index: 6114139 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5634. Min Act: -0.1700
Data Index: 3764233 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5477. Min Act: -0.1700
Data Index: 4636851 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5321. Min Act: -0.1700
Data Index: 3159889 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5477. Min Act: -0.1700
Data Index: 6779678 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5477. Min Act: -0.1700
Data Index: 3964908 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5321. Min Act: -0.1700
Data Index: 4940306 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5164. Min Act: -0.1700
Data Index: 8689110 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5321. Min Act: -0.1700
Data Index: 7105582 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5164. Min Act: -0.1700
Data Index: 1714566 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.5321. Min Act: -0.1700
Data Index: 5245796 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.4851. Min Act: -0.1700
Data Index: 6926046 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19