Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3796 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1134. Min Range: -8.1134
Max Act: 8.1134. Min Act: -0.1700
Data Index: 4013829 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.8009. Min Act: -0.1700
Data Index: 2718170 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.6759. Min Act: -0.1700
Data Index: 3983747 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.5197. Min Act: -0.1700
Data Index: 1279703 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.4884. Min Act: -0.1700
Data Index: 6216053 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.5197. Min Act: -0.1700
Data Index: 2018848 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.4884. Min Act: -0.1700
Data Index: 7327290 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.4572. Min Act: -0.1700
Data Index: 7482637 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.4259. Min Act: -0.1700
Data Index: 4331343 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.3947. Min Act: -0.1700
Data Index: 242716 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.3634. Min Act: -0.1700
Data Index: 3959677 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.3322. Min Act: -0.1700
Data Index: 1052215 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.3322. Min Act: -0.1700
Data Index: 1627566 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.3009. Min Act: -0.1700
Data Index: 7627177 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.3009. Min Act: -0.1700
Data Index: 1256691 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.3322. Min Act: -0.1700
Data Index: 7097626 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.3009. Min Act: -0.1700
Data Index: 2398421 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.2697. Min Act: -0.1700
Data Index: 3895469 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.2697. Min Act: -0.1700
Data Index: 426745 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1134. Min Range: -8.1134
Max Act: 7.2697. Min Act: -0.1700
Data Index: 6469432 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19