Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6222 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4004. Min Range: -9.4004
Max Act: 9.4004. Min Act: -0.1700
Data Index: 153813 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4004. Min Range: -9.4004
Max Act: 9.2129. Min Act: -0.1700
Data Index: 2227493 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4004. Min Range: -9.4004
Max Act: 9.0879. Min Act: -0.1700
Data Index: 4627164 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4004. Min Range: -9.4004
Max Act: 9.0254. Min Act: -0.1700
Data Index: 38996 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.9629. Min Act: -0.1700
Data Index: 7811610 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.9629. Min Act: -0.1700
Data Index: 7277890 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4004. Min Range: -9.4004
Max Act: 9.0254. Min Act: -0.1700
Data Index: 3339996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.9004. Min Act: -0.1700
Data Index: 6506844 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.8379. Min Act: -0.1700
Data Index: 8560033 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.8379. Min Act: -0.1700
Data Index: 6089282 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.8379. Min Act: -0.1700
Data Index: 2227510 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.8379. Min Act: -0.1700
Data Index: 6188371 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.7754. Min Act: -0.1700
Data Index: 916473 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.7754. Min Act: -0.1700
Data Index: 7523892 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.7754. Min Act: -0.1700
Data Index: 7431370 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.7754. Min Act: -0.1700
Data Index: 2227515 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.7754. Min Act: -0.1700
Data Index: 3866130 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.7754. Min Act: -0.1700
Data Index: 758251 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.7754. Min Act: -0.1700
Data Index: 5325270 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4004. Min Range: -9.4004
Max Act: 8.7129. Min Act: -0.1700
Data Index: 1228498 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19