Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3717 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.1252. Min Act: -0.1700
Data Index: 7675009 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.1085. Min Act: -0.1700
Data Index: 3363351 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0918. Min Act: -0.1700
Data Index: 6984788 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0582. Min Act: -0.1700
Data Index: 5964551 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0414. Min Act: -0.1700
Data Index: 7847330 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0414. Min Act: -0.1700
Data Index: 7763914 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0414. Min Act: -0.1700
Data Index: 4349703 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0245. Min Act: -0.1700
Data Index: 277811 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0245. Min Act: -0.1700
Data Index: 7173492 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0245. Min Act: -0.1699
Data Index: 397603 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0245. Min Act: -0.1700
Data Index: 87566 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0245. Min Act: -0.1700
Data Index: 3797984 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0077. Min Act: -0.1700
Data Index: 1187314 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0245. Min Act: -0.1700
Data Index: 6318176 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0077. Min Act: -0.1700
Data Index: 2957087 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0077. Min Act: -0.1700
Data Index: 681041 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0077. Min Act: -0.1698
Data Index: 4553833 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0077. Min Act: -0.1700
Data Index: 7888848 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1252. Min Range: -2.1252
Max Act: 2.0077. Min Act: -0.1700
Data Index: 5673837 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1252. Min Range: -2.1252
Max Act: 1.9908. Min Act: -0.1700
Data Index: 3382112 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19