Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7846. Min Act: -0.1700
Data Index: 1501467 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7501. Min Act: -0.1700
Data Index: 6048264 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7501. Min Act: -0.1700
Data Index: 1037688 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7328. Min Act: -0.1700
Data Index: 2519978 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7328. Min Act: -0.1700
Data Index: 1926398 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7328. Min Act: -0.1700
Data Index: 409508 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7155. Min Act: -0.1696
Data Index: 6601179 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7155. Min Act: -0.1691
Data Index: 1126014 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7241. Min Act: -0.1700
Data Index: 5310949 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7155. Min Act: -0.1700
Data Index: 3054727 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7155. Min Act: -0.1700
Data Index: 2701593 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.6895. Min Act: -0.1700
Data Index: 4543354 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.6981. Min Act: -0.1700
Data Index: 5070443 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.7068. Min Act: -0.1700
Data Index: 814694 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.6981. Min Act: -0.1700
Data Index: 7293971 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.6808. Min Act: -0.1700
Data Index: 2104833 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.6981. Min Act: -0.1699
Data Index: 3681510 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.6895. Min Act: -0.1700
Data Index: 1455319 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.6808. Min Act: -0.1699
Data Index: 6397595 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7846. Min Range: -1.7846
Max Act: 1.6895. Min Act: -0.1700
Data Index: 5699468 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19