Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2515 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3973. Min Range: -6.3973
Max Act: 6.3973. Min Act: -0.1700
Data Index: 5199458 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3973. Min Range: -6.3973
Max Act: 6.3973. Min Act: -0.1700
Data Index: 1463838 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3973. Min Range: -6.3973
Max Act: 6.1473. Min Act: -0.1700
Data Index: 1308057 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3973. Min Range: -6.3973
Max Act: 6.1473. Min Act: -0.1700
Data Index: 1923779 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3973. Min Range: -6.3973
Max Act: 6.1160. Min Act: -0.1700
Data Index: 8090939 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3973. Min Range: -6.3973
Max Act: 6.0848. Min Act: -0.1700
Data Index: 4256235 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3973. Min Range: -6.3973
Max Act: 6.0223. Min Act: -0.1700
Data Index: 2616373 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.9910. Min Act: -0.1700
Data Index: 6354445 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.9910. Min Act: -0.1700
Data Index: 1890961 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.9910. Min Act: -0.1700
Data Index: 1608407 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.9598. Min Act: -0.1700
Data Index: 4579790 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.9285. Min Act: -0.1700
Data Index: 6327275 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.8973. Min Act: -0.1700
Data Index: 6432649 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.8973. Min Act: -0.1700
Data Index: 6096993 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.8660. Min Act: -0.1700
Data Index: 5094615 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.8348. Min Act: -0.1700
Data Index: 5302977 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.8035. Min Act: -0.1700
Data Index: 5875064 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.7723. Min Act: -0.1700
Data Index: 520285 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.8035. Min Act: -0.1700
Data Index: 874912 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3973. Min Range: -6.3973
Max Act: 5.8035. Min Act: -0.1700
Data Index: 7566711 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19