Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.4254. Min Act: -0.1700
Data Index: 3136384 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.3942. Min Act: -0.1700
Data Index: 8071280 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.3004. Min Act: -0.1700
Data Index: 4902120 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.2379. Min Act: -0.1700
Data Index: 4823012 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.2067. Min Act: -0.1700
Data Index: 528241 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.2067. Min Act: -0.1700
Data Index: 7576585 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.2067. Min Act: -0.1700
Data Index: 1844477 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.1754. Min Act: -0.1700
Data Index: 3766682 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.1129. Min Act: -0.1700
Data Index: 236460 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.1129. Min Act: -0.1700
Data Index: 4012058 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.0817. Min Act: -0.1700
Data Index: 2590319 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.0817. Min Act: -0.1700
Data Index: 6082497 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.0817. Min Act: -0.1700
Data Index: 2734075 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.0192. Min Act: -0.1700
Data Index: 1586483 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.0817. Min Act: -0.1700
Data Index: 5344034 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.0192. Min Act: -0.1700
Data Index: 6714477 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.0504. Min Act: -0.1700
Data Index: 6188555 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.0192. Min Act: -0.1700
Data Index: 5400786 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.0504. Min Act: -0.1700
Data Index: 6687143 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4254. Min Range: -6.4254
Max Act: 6.0504. Min Act: -0.1700
Data Index: 2731652 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19