Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1092 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.8185. Min Act: -0.1700
Data Index: 4502690 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.7707. Min Act: -0.1700
Data Index: 5151894 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.7068. Min Act: -0.1700
Data Index: 177646 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.7068. Min Act: -0.1700
Data Index: 2111293 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6908. Min Act: -0.1700
Data Index: 7133370 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6748. Min Act: -0.1700
Data Index: 2946163 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6587. Min Act: -0.1700
Data Index: 5009747 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6587. Min Act: -0.1700
Data Index: 2825231 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6748. Min Act: -0.1700
Data Index: 2536995 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6587. Min Act: -0.1700
Data Index: 2378194 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6266. Min Act: -0.1700
Data Index: 2459047 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6427. Min Act: -0.1700
Data Index: 5587822 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6427. Min Act: -0.1700
Data Index: 1505863 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6266. Min Act: -0.1700
Data Index: 6374031 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6427. Min Act: -0.1700
Data Index: 687466 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6266. Min Act: -0.1700
Data Index: 3025349 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6266. Min Act: -0.1700
Data Index: 5944625 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6266. Min Act: -0.1700
Data Index: 422468 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6266. Min Act: -0.1700
Data Index: 2557534 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8185. Min Range: -2.8185
Max Act: 2.6427. Min Act: -0.1700
Data Index: 7351626 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19