Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4640 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.4348. Min Act: -0.1700
Data Index: 8470040 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.4036. Min Act: -0.1700
Data Index: 8696615 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.3723. Min Act: -0.1700
Data Index: 1834435 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.2473. Min Act: -0.1700
Data Index: 4660945 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.2161. Min Act: -0.1700
Data Index: 6890351 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.1536. Min Act: -0.1700
Data Index: 4666873 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.1848. Min Act: -0.1700
Data Index: 6837214 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.1536. Min Act: -0.1700
Data Index: 2577383 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.1536. Min Act: -0.1700
Data Index: 6158171 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.0911. Min Act: -0.1700
Data Index: 8524073 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.0911. Min Act: -0.1700
Data Index: 4666876 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.1223. Min Act: -0.1700
Data Index: 3442008 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.0598. Min Act: -0.1700
Data Index: 5364924 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.0598. Min Act: -0.1700
Data Index: 5444623 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4348. Min Range: -5.4348
Max Act: 5.0598. Min Act: -0.1700
Data Index: 7395669 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4348. Min Range: -5.4348
Max Act: 4.9661. Min Act: -0.1700
Data Index: 3992667 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4348. Min Range: -5.4348
Max Act: 4.9973. Min Act: -0.1700
Data Index: 1834663 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4348. Min Range: -5.4348
Max Act: 4.9661. Min Act: -0.1700
Data Index: 2461879 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4348. Min Range: -5.4348
Max Act: 4.9661. Min Act: -0.1700
Data Index: 7705715 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4348. Min Range: -5.4348
Max Act: 4.9661. Min Act: -0.1700
Data Index: 2491346 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19