Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 975 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6180. Min Act: -0.1700
Data Index: 7994238 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6354. Min Act: -0.1700
Data Index: 7160695 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6354. Min Act: -0.1700
Data Index: 6756498 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6267. Min Act: -0.1700
Data Index: 3623093 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6005. Min Act: -0.1696
Data Index: 8312011 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6180. Min Act: -0.1700
Data Index: 1117884 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6092. Min Act: -0.1692
Data Index: 2561328 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6092. Min Act: -0.1700
Data Index: 1875752 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6180. Min Act: -0.1676
Data Index: 2785640 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6180. Min Act: -0.1669
Data Index: 2644885 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6180. Min Act: -0.1700
Data Index: 4455097 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6092. Min Act: -0.1690
Data Index: 3030437 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6180. Min Act: -0.1700
Data Index: 6345840 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6092. Min Act: -0.1700
Data Index: 312141 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.5918. Min Act: -0.1700
Data Index: 2491544 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6005. Min Act: -0.1700
Data Index: 644129 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.5918. Min Act: -0.1700
Data Index: 6715196 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6005. Min Act: -0.1700
Data Index: 2551916 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6005. Min Act: -0.1700
Data Index: 5961088 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6354. Min Range: -1.6354
Max Act: 1.6092. Min Act: -0.1700
Data Index: 2131663 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19