Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1706 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.6125. Min Act: -0.1700
Data Index: 1821321 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.6125. Min Act: -0.1700
Data Index: 1269536 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.6125. Min Act: -0.1700
Data Index: 5952864 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5813. Min Act: -0.1700
Data Index: 6568545 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.6125. Min Act: -0.1700
Data Index: 2731477 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5813. Min Act: -0.1700
Data Index: 3560862 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5813. Min Act: -0.1700
Data Index: 1685299 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5813. Min Act: -0.1700
Data Index: 2809443 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5813. Min Act: -0.1700
Data Index: 7602965 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5813. Min Act: -0.1700
Data Index: 24337 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5813. Min Act: -0.1700
Data Index: 7101677 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5813. Min Act: -0.1700
Data Index: 3516676 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5813. Min Act: -0.1700
Data Index: 8505505 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5500. Min Act: -0.1700
Data Index: 3778062 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5813. Min Act: -0.1700
Data Index: 1525842 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5500. Min Act: -0.1700
Data Index: 7058928 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5500. Min Act: -0.1700
Data Index: 2058002 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5500. Min Act: -0.1700
Data Index: 7350108 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5500. Min Act: -0.1700
Data Index: 5407942 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6125. Min Range: -4.6125
Max Act: 4.5500. Min Act: -0.1700
Data Index: 2933578 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19