Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 163 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.5115. Min Act: -0.1700
Data Index: 2356678 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.4490. Min Act: -0.1700
Data Index: 4468156 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.3552. Min Act: -0.1700
Data Index: 5629687 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.3552. Min Act: -0.1700
Data Index: 5840129 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.3240. Min Act: -0.1700
Data Index: 4622487 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.3552. Min Act: -0.1700
Data Index: 1893934 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.3240. Min Act: -0.1700
Data Index: 3430610 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2615. Min Act: -0.1700
Data Index: 4814333 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2615. Min Act: -0.1700
Data Index: 5006039 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2927. Min Act: -0.1700
Data Index: 8011884 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2927. Min Act: -0.1700
Data Index: 4489593 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2927. Min Act: -0.1700
Data Index: 5528176 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2615. Min Act: -0.1700
Data Index: 478884 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2615. Min Act: -0.1700
Data Index: 3778819 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2302. Min Act: -0.1700
Data Index: 2480746 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2302. Min Act: -0.1700
Data Index: 5112 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2615. Min Act: -0.1700
Data Index: 3428624 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2615. Min Act: -0.1700
Data Index: 1275367 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2927. Min Act: -0.1700
Data Index: 5488724 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5115. Min Range: -5.5115
Max Act: 5.2615. Min Act: -0.1700
Data Index: 5223623 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19