Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 751 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.5159. Min Act: -0.1700
Data Index: 5629354 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.5159. Min Act: -0.1700
Data Index: 1415527 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.4847. Min Act: -0.1700
Data Index: 7376539 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.4534. Min Act: -0.1700
Data Index: 3788538 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.4222. Min Act: -0.1700
Data Index: 4465656 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.4222. Min Act: -0.1700
Data Index: 7591776 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.4222. Min Act: -0.1700
Data Index: 3607161 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.4222. Min Act: -0.1700
Data Index: 6991567 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.3909. Min Act: -0.1700
Data Index: 3990085 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.3909. Min Act: -0.1700
Data Index: 2425673 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.4222. Min Act: -0.1700
Data Index: 6887890 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.3909. Min Act: -0.1700
Data Index: 4713089 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.3909. Min Act: -0.1700
Data Index: 7409175 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.3596. Min Act: -0.1700
Data Index: 1705375 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.3596. Min Act: -0.1700
Data Index: 6887891 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.3596. Min Act: -0.1700
Data Index: 3596191 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.3596. Min Act: -0.1700
Data Index: 720123 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.3284. Min Act: -0.1700
Data Index: 2291436 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.3909. Min Act: -0.1700
Data Index: 8578912 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5159. Min Range: -4.5159
Max Act: 4.3596. Min Act: -0.1700
Data Index: 2516799 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19