Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.3207. Min Act: -0.1700
Data Index: 1098399 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.2942. Min Act: -0.1692
Data Index: 4202415 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.2678. Min Act: -0.1699
Data Index: 1988764 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.2678. Min Act: -0.1694
Data Index: 3109131 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.2325. Min Act: -0.1671
Data Index: 4602414 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.2325. Min Act: -0.1700
Data Index: 4243254 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.2149. Min Act: -0.1700
Data Index: 7504734 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.2237. Min Act: -0.1681
Data Index: 4658585 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.2149. Min Act: -0.1699
Data Index: 4041816 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.2237. Min Act: -0.1698
Data Index: 4654926 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.2061. Min Act: -0.1698
Data Index: 1167372 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.1973. Min Act: -0.1700
Data Index: 4682845 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.1973. Min Act: -0.1696
Data Index: 1279683 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.1973. Min Act: -0.1699
Data Index: 2630525 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.1885. Min Act: -0.1700
Data Index: 4237697 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.1885. Min Act: -0.1681
Data Index: 8349913 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.1885. Min Act: -0.1700
Data Index: 8412370 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.1885. Min Act: -0.1700
Data Index: 7284529 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.1973. Min Act: -0.1700
Data Index: 6170246 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3207. Min Range: -1.3207
Max Act: 1.1797. Min Act: -0.1700
Data Index: 4728974 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19