Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2358 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1967. Min Range: -11.1967
Max Act: 11.1967. Min Act: -0.1700
Data Index: 2302729 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1967. Min Range: -11.1967
Max Act: 11.1342. Min Act: -0.1700
Data Index: 7669534 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1967. Min Range: -11.1967
Max Act: 11.0092. Min Act: -0.1700
Data Index: 3932030 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.7592. Min Act: -0.1700
Data Index: 8318131 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.7592. Min Act: -0.1700
Data Index: 5863491 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.7592. Min Act: -0.1700
Data Index: 8255126 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.6967. Min Act: -0.1700
Data Index: 6984212 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.6342. Min Act: -0.1700
Data Index: 801662 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.6342. Min Act: -0.1700
Data Index: 6144164 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.6342. Min Act: -0.1700
Data Index: 4647866 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.6342. Min Act: -0.1700
Data Index: 7822331 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.5717. Min Act: -0.1700
Data Index: 5342707 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.5717. Min Act: -0.1700
Data Index: 794678 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.5717. Min Act: -0.1700
Data Index: 2640770 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.5717. Min Act: -0.1700
Data Index: 4931446 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.5717. Min Act: -0.1700
Data Index: 3403101 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.5717. Min Act: -0.1700
Data Index: 114035 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.5717. Min Act: -0.1700
Data Index: 4311063 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.5092. Min Act: -0.1700
Data Index: 3178534 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1967. Min Range: -11.1967
Max Act: 10.4467. Min Act: -0.1700
Data Index: 5503867 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19