Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3133 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1196. Min Range: -4.1196
Max Act: 4.1196. Min Act: -0.1700
Data Index: 4026833 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1196. Min Range: -4.1196
Max Act: 4.0883. Min Act: -0.1700
Data Index: 1780003 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1196. Min Range: -4.1196
Max Act: 4.0883. Min Act: -0.1700
Data Index: 875036 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.9633. Min Act: -0.1700
Data Index: 2643250 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.9945. Min Act: -0.1700
Data Index: 6115634 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.9945. Min Act: -0.1700
Data Index: 2808919 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.9007. Min Act: -0.1700
Data Index: 4317591 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.9320. Min Act: -0.1700
Data Index: 5202517 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.9007. Min Act: -0.1700
Data Index: 2190171 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.9007. Min Act: -0.1700
Data Index: 315351 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.8695. Min Act: -0.1700
Data Index: 3670479 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.8695. Min Act: -0.1700
Data Index: 7565835 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.8695. Min Act: -0.1700
Data Index: 1517897 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.8695. Min Act: -0.1700
Data Index: 4029728 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.8695. Min Act: -0.1700
Data Index: 8193313 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.8695. Min Act: -0.1700
Data Index: 4047025 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.8695. Min Act: -0.1700
Data Index: 4031069 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.8069. Min Act: -0.1700
Data Index: 857310 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.8069. Min Act: -0.1700
Data Index: 7020099 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1196. Min Range: -4.1196
Max Act: 3.8382. Min Act: -0.1700
Data Index: 3705320 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19