Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.7030. Min Act: -0.1700
Data Index: 1650779 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.5467. Min Act: -0.1700
Data Index: 1026941 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.5155. Min Act: -0.1700
Data Index: 8481116 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.4842. Min Act: -0.1700
Data Index: 8470532 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.4217. Min Act: -0.1700
Data Index: 7102854 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.4217. Min Act: -0.1700
Data Index: 3496606 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3905. Min Act: -0.1700
Data Index: 2666935 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3905. Min Act: -0.1700
Data Index: 5227552 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3592. Min Act: -0.1700
Data Index: 6329520 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3592. Min Act: -0.1700
Data Index: 4958058 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3592. Min Act: -0.1700
Data Index: 8704802 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3592. Min Act: -0.1700
Data Index: 4751252 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3592. Min Act: -0.1700
Data Index: 7054988 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3592. Min Act: -0.1700
Data Index: 6786534 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3592. Min Act: -0.1700
Data Index: 2268327 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3592. Min Act: -0.1700
Data Index: 1461572 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3905. Min Act: -0.1700
Data Index: 6595931 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3592. Min Act: -0.1700
Data Index: 1397258 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3280. Min Act: -0.1700
Data Index: 4859021 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7030. Min Range: -5.7030
Max Act: 5.3280. Min Act: -0.1700
Data Index: 5059443 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19