Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3765 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.7151. Min Act: -0.1700
Data Index: 4907840 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6978. Min Act: -0.1700
Data Index: 1064611 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6805. Min Act: -0.1700
Data Index: 4125548 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6718. Min Act: -0.1700
Data Index: 1284261 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6631. Min Act: -0.1699
Data Index: 7013473 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6544. Min Act: -0.1694
Data Index: 5607819 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6370. Min Act: -0.1700
Data Index: 7405370 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6457. Min Act: -0.1700
Data Index: 5636496 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6370. Min Act: -0.1700
Data Index: 1801034 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6457. Min Act: -0.1700
Data Index: 4478006 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6283. Min Act: -0.1700
Data Index: 762818 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6195. Min Act: -0.1700
Data Index: 1962768 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6283. Min Act: -0.1700
Data Index: 1535400 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6195. Min Act: -0.1700
Data Index: 2350495 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6283. Min Act: -0.1700
Data Index: 7981416 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6195. Min Act: -0.1698
Data Index: 137015 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6195. Min Act: -0.1700
Data Index: 8585928 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6195. Min Act: -0.1699
Data Index: 3107705 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6195. Min Act: -0.1700
Data Index: 1498097 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7151. Min Range: -1.7151
Max Act: 1.6195. Min Act: -0.1700
Data Index: 4807014 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19