Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4521 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1085. Min Range: -5.1085
Max Act: 5.1085. Min Act: -0.1700
Data Index: 149095 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.9835. Min Act: -0.1700
Data Index: 1948146 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.9835. Min Act: -0.1700
Data Index: 2877785 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.9523. Min Act: -0.1700
Data Index: 394897 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.9523. Min Act: -0.1700
Data Index: 3419163 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.9210. Min Act: -0.1700
Data Index: 499454 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.9210. Min Act: -0.1700
Data Index: 2634619 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8585. Min Act: -0.1700
Data Index: 3658358 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.9210. Min Act: -0.1700
Data Index: 3157300 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8898. Min Act: -0.1700
Data Index: 6377334 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8898. Min Act: -0.1700
Data Index: 8367085 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8898. Min Act: -0.1700
Data Index: 5180602 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8898. Min Act: -0.1700
Data Index: 1777341 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8585. Min Act: -0.1700
Data Index: 6448399 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8585. Min Act: -0.1700
Data Index: 7167143 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8273. Min Act: -0.1700
Data Index: 1734542 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8585. Min Act: -0.1700
Data Index: 725265 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8898. Min Act: -0.1700
Data Index: 8065394 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8273. Min Act: -0.1700
Data Index: 38821 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1085. Min Range: -5.1085
Max Act: 4.8273. Min Act: -0.1700
Data Index: 5608696 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19