Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 584 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.7265. Min Act: -0.1697
Data Index: 159526 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.7265. Min Act: -0.1700
Data Index: 1380016 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.4765. Min Act: -0.1700
Data Index: 4187458 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.3515. Min Act: -0.1700
Data Index: 3017000 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.4765. Min Act: -0.1700
Data Index: 221842 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.2265. Min Act: -0.1700
Data Index: 846190 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.2265. Min Act: -0.1697
Data Index: 7967195 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.2265. Min Act: -0.1700
Data Index: 5885373 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.2265. Min Act: -0.1700
Data Index: 5095196 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.7265. Min Range: -19.7265
Max Act: 18.9765. Min Act: -0.1698
Data Index: 8765271 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.2265. Min Act: -0.1699
Data Index: 5484579 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.7265. Min Range: -19.7265
Max Act: 18.9765. Min Act: -0.1700
Data Index: 8803402 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.2265. Min Act: -0.1700
Data Index: 4651672 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.7265. Min Range: -19.7265
Max Act: 19.1015. Min Act: -0.1693
Data Index: 3208238 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.7265. Min Range: -19.7265
Max Act: 18.9765. Min Act: -0.1683
Data Index: 6556898 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.7265. Min Range: -19.7265
Max Act: 18.7265. Min Act: -0.1683
Data Index: 5871301 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.7265. Min Range: -19.7265
Max Act: 18.9765. Min Act: -0.1700
Data Index: 7108566 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.7265. Min Range: -19.7265
Max Act: 18.9765. Min Act: -0.1700
Data Index: 2906714 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.7265. Min Range: -19.7265
Max Act: 18.7265. Min Act: -0.1601
Data Index: 191396 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.7265. Min Range: -19.7265
Max Act: 18.8515. Min Act: -0.1700
Data Index: 4948423 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19