Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 281 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1121. Min Range: -4.1121
Max Act: 4.1121. Min Act: -0.1700
Data Index: 3267297 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1121. Min Range: -4.1121
Max Act: 4.0183. Min Act: -0.1700
Data Index: 8201409 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1121. Min Range: -4.1121
Max Act: 4.0183. Min Act: -0.1700
Data Index: 3327915 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9870. Min Act: -0.1700
Data Index: 5473166 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9870. Min Act: -0.1700
Data Index: 7775976 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9870. Min Act: -0.1700
Data Index: 1790915 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9870. Min Act: -0.1700
Data Index: 135349 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1121. Min Range: -4.1121
Max Act: 4.0183. Min Act: -0.1700
Data Index: 8792950 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9558. Min Act: -0.1700
Data Index: 1180652 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9245. Min Act: -0.1700
Data Index: 7849726 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9245. Min Act: -0.1700
Data Index: 1012202 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9558. Min Act: -0.1700
Data Index: 490900 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9870. Min Act: -0.1700
Data Index: 2349682 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9245. Min Act: -0.1700
Data Index: 5390048 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.8932. Min Act: -0.1700
Data Index: 6090038 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9245. Min Act: -0.1700
Data Index: 3265524 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9245. Min Act: -0.1700
Data Index: 8109188 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9558. Min Act: -0.1700
Data Index: 6958562 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.9245. Min Act: -0.1700
Data Index: 2349683 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1121. Min Range: -4.1121
Max Act: 3.8620. Min Act: -0.1700
Data Index: 7526840 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19