Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4583 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4007. Min Range: -9.4007
Max Act: 9.4007. Min Act: -0.1700
Data Index: 5451060 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4007. Min Range: -9.4007
Max Act: 9.2757. Min Act: -0.1700
Data Index: 2272195 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4007. Min Range: -9.4007
Max Act: 9.0257. Min Act: -0.1700
Data Index: 1866830 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4007. Min Range: -9.4007
Max Act: 9.0257. Min Act: -0.1700
Data Index: 1866831 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.9632. Min Act: -0.1700
Data Index: 1680263 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.8382. Min Act: -0.1700
Data Index: 6334755 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.7132. Min Act: -0.1700
Data Index: 4770748 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.6507. Min Act: -0.1700
Data Index: 2272201 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.6507. Min Act: -0.1700
Data Index: 7165474 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.6507. Min Act: -0.1700
Data Index: 2774210 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.6507. Min Act: -0.1700
Data Index: 6017812 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.5882. Min Act: -0.1700
Data Index: 6334756 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.5257. Min Act: -0.1700
Data Index: 3417807 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.5882. Min Act: -0.1700
Data Index: 664038 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.5257. Min Act: -0.1700
Data Index: 4224844 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.5257. Min Act: -0.1700
Data Index: 2781727 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.5257. Min Act: -0.1700
Data Index: 1775300 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.4632. Min Act: -0.1700
Data Index: 2709963 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.4632. Min Act: -0.1700
Data Index: 3854245 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4007. Min Range: -9.4007
Max Act: 8.4632. Min Act: -0.1700
Data Index: 4842916 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19