Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 107 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0928. Min Range: -8.0928
Max Act: 8.0928. Min Act: -0.1700
Data Index: 4891972 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.9053. Min Act: -0.1700
Data Index: 232748 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.8115. Min Act: -0.1700
Data Index: 5742235 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.7803. Min Act: -0.1700
Data Index: 6666150 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.7178. Min Act: -0.1700
Data Index: 4891973 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.5615. Min Act: -0.1700
Data Index: 6666146 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.7178. Min Act: -0.1700
Data Index: 6666145 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.5928. Min Act: -0.1700
Data Index: 4891971 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.5615. Min Act: -0.1700
Data Index: 980658 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.5615. Min Act: -0.1700
Data Index: 6666147 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.5615. Min Act: -0.1700
Data Index: 4891974 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.4678. Min Act: -0.1700
Data Index: 8627676 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.4365. Min Act: -0.1700
Data Index: 6666148 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.4990. Min Act: -0.1700
Data Index: 4671125 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.4678. Min Act: -0.1700
Data Index: 5742240 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.4365. Min Act: -0.1700
Data Index: 980652 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.4990. Min Act: -0.1700
Data Index: 6666144 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.4365. Min Act: -0.1700
Data Index: 4671126 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.4365. Min Act: -0.1700
Data Index: 4671133 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0928. Min Range: -8.0928
Max Act: 7.4053. Min Act: -0.1700
Data Index: 1458228 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19