Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4067. Min Range: -6.4067
Max Act: 6.4067. Min Act: -0.1700
Data Index: 7039683 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.9380. Min Act: -0.1700
Data Index: 6987 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.8755. Min Act: -0.1700
Data Index: 4775719 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.8755. Min Act: -0.1700
Data Index: 2502070 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.8442. Min Act: -0.1700
Data Index: 4777187 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.8442. Min Act: -0.1700
Data Index: 8331646 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.7817. Min Act: -0.1700
Data Index: 5648841 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.7192. Min Act: -0.1700
Data Index: 1721355 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.6567. Min Act: -0.1700
Data Index: 5176443 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.6255. Min Act: -0.1700
Data Index: 8113081 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.5942. Min Act: -0.1700
Data Index: 3754392 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.6255. Min Act: -0.1700
Data Index: 5412150 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.6255. Min Act: -0.1700
Data Index: 5207017 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.5630. Min Act: -0.1700
Data Index: 5876112 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.5630. Min Act: -0.1700
Data Index: 6894506 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.5630. Min Act: -0.1700
Data Index: 778955 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.5630. Min Act: -0.1700
Data Index: 6016421 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.5317. Min Act: -0.1700
Data Index: 5772986 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.5005. Min Act: -0.1700
Data Index: 699217 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4067. Min Range: -6.4067
Max Act: 5.5005. Min Act: -0.1700
Data Index: 5877550 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19