Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3904 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.4254. Min Act: -0.1700
Data Index: 4502138 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.3629. Min Act: -0.1700
Data Index: 8405482 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.2691. Min Act: -0.1700
Data Index: 1177438 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.2379. Min Act: -0.1700
Data Index: 1059666 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.1754. Min Act: -0.1700
Data Index: 1902315 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.2066. Min Act: -0.1700
Data Index: 32764 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.1754. Min Act: -0.1700
Data Index: 8093251 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.2066. Min Act: -0.1700
Data Index: 4214634 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.1754. Min Act: -0.1700
Data Index: 1747282 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.1441. Min Act: -0.1700
Data Index: 1445917 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.1754. Min Act: -0.1700
Data Index: 3281698 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.1441. Min Act: -0.1700
Data Index: 3646717 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.1441. Min Act: -0.1700
Data Index: 7738444 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.1129. Min Act: -0.1700
Data Index: 5895843 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.1129. Min Act: -0.1700
Data Index: 5320166 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.0816. Min Act: -0.1700
Data Index: 5224997 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.0816. Min Act: -0.1700
Data Index: 1428790 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.0191. Min Act: -0.1700
Data Index: 7597467 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.0504. Min Act: -0.1700
Data Index: 2551770 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4254. Min Range: -7.4254
Max Act: 7.0191. Min Act: -0.1700
Data Index: 4500689 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19