Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3907 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.9719. Min Act: -0.1700
Data Index: 2339530 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.9549. Min Act: -0.1700
Data Index: 324101 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.9549. Min Act: -0.1699
Data Index: 6404936 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.9549. Min Act: -0.1700
Data Index: 6404939 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.9549. Min Act: -0.1700
Data Index: 748172 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.9039. Min Act: -0.1700
Data Index: 5602646 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.9039. Min Act: -0.1700
Data Index: 6853984 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8868. Min Act: -0.1700
Data Index: 2545252 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8697. Min Act: -0.1700
Data Index: 5602663 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8868. Min Act: -0.1700
Data Index: 6846114 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8868. Min Act: -0.1700
Data Index: 4534368 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8868. Min Act: -0.1700
Data Index: 4823078 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8526. Min Act: -0.1700
Data Index: 1265619 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8526. Min Act: -0.1700
Data Index: 8756199 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8697. Min Act: -0.1700
Data Index: 4869904 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8526. Min Act: -0.1700
Data Index: 8756201 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8526. Min Act: -0.1700
Data Index: 748179 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8355. Min Act: -0.1700
Data Index: 8756180 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8526. Min Act: -0.1700
Data Index: 8723595 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9719. Min Range: -1.9719
Max Act: 1.8355. Min Act: -0.1700
Data Index: 8183166 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19