Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.9300. Min Act: -0.1700
Data Index: 8590977 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.8363. Min Act: -0.1700
Data Index: 2178419 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.5238. Min Act: -0.1700
Data Index: 6952480 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4925. Min Act: -0.1700
Data Index: 1694525 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.5238. Min Act: -0.1700
Data Index: 6521549 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4300. Min Act: -0.1700
Data Index: 4819710 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.3675. Min Act: -0.1700
Data Index: 846010 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.3363. Min Act: -0.1700
Data Index: 833616 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.3363. Min Act: -0.1700
Data Index: 7701171 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.3363. Min Act: -0.1700
Data Index: 669055 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.3050. Min Act: -0.1700
Data Index: 3795474 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.3050. Min Act: -0.1700
Data Index: 7757940 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.3050. Min Act: -0.1700
Data Index: 8725274 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.3050. Min Act: -0.1700
Data Index: 1388557 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.3050. Min Act: -0.1700
Data Index: 5272054 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.2738. Min Act: -0.1700
Data Index: 5231961 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.2113. Min Act: -0.1700
Data Index: 5669032 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.2113. Min Act: -0.1700
Data Index: 4348544 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.2113. Min Act: -0.1700
Data Index: 2866032 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.2113. Min Act: -0.1700
Data Index: 8197995 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19