Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4363 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3367. Min Range: -5.3367
Max Act: 5.3367. Min Act: -0.1700
Data Index: 2461047 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3367. Min Range: -5.3367
Max Act: 5.1805. Min Act: -0.1700
Data Index: 4423765 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3367. Min Range: -5.3367
Max Act: 5.1492. Min Act: -0.1700
Data Index: 3547734 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3367. Min Range: -5.3367
Max Act: 5.0555. Min Act: -0.1700
Data Index: 5326606 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3367. Min Range: -5.3367
Max Act: 5.0555. Min Act: -0.1700
Data Index: 2558510 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3367. Min Range: -5.3367
Max Act: 5.0242. Min Act: -0.1700
Data Index: 2043729 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3367. Min Range: -5.3367
Max Act: 5.0242. Min Act: -0.1700
Data Index: 6798390 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.9930. Min Act: -0.1700
Data Index: 6456461 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.9305. Min Act: -0.1700
Data Index: 5486088 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.9305. Min Act: -0.1700
Data Index: 4907837 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.8992. Min Act: -0.1700
Data Index: 77799 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.8992. Min Act: -0.1700
Data Index: 6045231 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.9305. Min Act: -0.1700
Data Index: 6739985 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.8992. Min Act: -0.1700
Data Index: 4519913 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.8367. Min Act: -0.1700
Data Index: 7280687 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.8367. Min Act: -0.1700
Data Index: 2674374 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.8367. Min Act: -0.1700
Data Index: 7331671 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.8367. Min Act: -0.1700
Data Index: 710084 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.8367. Min Act: -0.1700
Data Index: 5985334 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3367. Min Range: -5.3367
Max Act: 4.8367. Min Act: -0.1700
Data Index: 1548260 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19