Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.3236. Min Act: -0.1700
Data Index: 1025645 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.2611. Min Act: -0.1700
Data Index: 6729845 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.2299. Min Act: -0.1700
Data Index: 2860839 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.1986. Min Act: -0.1700
Data Index: 3823379 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.2299. Min Act: -0.1700
Data Index: 3003359 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.1986. Min Act: -0.1700
Data Index: 8228348 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.1361. Min Act: -0.1700
Data Index: 2548506 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.1674. Min Act: -0.1700
Data Index: 8544721 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.1361. Min Act: -0.1700
Data Index: 104443 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.1049. Min Act: -0.1700
Data Index: 6645817 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.0736. Min Act: -0.1700
Data Index: 5912503 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.0111. Min Act: -0.1700
Data Index: 2035971 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.0424. Min Act: -0.1700
Data Index: 4255239 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.0111. Min Act: -0.1700
Data Index: 6006446 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.0111. Min Act: -0.1700
Data Index: 1229333 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.0111. Min Act: -0.1700
Data Index: 104761 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.0424. Min Act: -0.1700
Data Index: 6552735 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3236. Min Range: -5.3236
Max Act: 5.0111. Min Act: -0.1700
Data Index: 7966823 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3236. Min Range: -5.3236
Max Act: 4.9799. Min Act: -0.1700
Data Index: 4339065 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3236. Min Range: -5.3236
Max Act: 4.9799. Min Act: -0.1700
Data Index: 6259998 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19