Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 122 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.5384. Min Act: -0.1700
Data Index: 427941 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.5384. Min Act: -0.1700
Data Index: 8179385 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.5384. Min Act: -0.1700
Data Index: 5060334 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.5072. Min Act: -0.1700
Data Index: 166676 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.4759. Min Act: -0.1700
Data Index: 7010357 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.4759. Min Act: -0.1700
Data Index: 2768757 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.4447. Min Act: -0.1700
Data Index: 6252925 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.4447. Min Act: -0.1700
Data Index: 6371895 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3822. Min Act: -0.1700
Data Index: 2460321 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.4134. Min Act: -0.1700
Data Index: 8828707 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3822. Min Act: -0.1700
Data Index: 1144194 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3509. Min Act: -0.1700
Data Index: 6445095 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3509. Min Act: -0.1700
Data Index: 1682605 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3197. Min Act: -0.1700
Data Index: 5586916 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3197. Min Act: -0.1700
Data Index: 5804742 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3197. Min Act: -0.1700
Data Index: 551226 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3509. Min Act: -0.1700
Data Index: 4415807 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3197. Min Act: -0.1700
Data Index: 1561257 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.2884. Min Act: -0.1700
Data Index: 8696292 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.2884. Min Act: -0.1700
Data Index: 7362959 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19