Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2831 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.8906. Min Act: -0.1700
Data Index: 579385 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.8281. Min Act: -0.1700
Data Index: 2402820 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.7656. Min Act: -0.1700
Data Index: 4778523 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.6406. Min Act: -0.1700
Data Index: 747613 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.6406. Min Act: -0.1700
Data Index: 5475371 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.6406. Min Act: -0.1700
Data Index: 3209557 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.6094. Min Act: -0.1700
Data Index: 1998611 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.6406. Min Act: -0.1700
Data Index: 5712425 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.6094. Min Act: -0.1700
Data Index: 98376 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.6094. Min Act: -0.1700
Data Index: 2231780 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.5781. Min Act: -0.1700
Data Index: 8671582 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.5781. Min Act: -0.1700
Data Index: 6831675 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.5781. Min Act: -0.1700
Data Index: 7970887 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.5469. Min Act: -0.1700
Data Index: 1840517 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.5781. Min Act: -0.1700
Data Index: 2545902 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.5781. Min Act: -0.1700
Data Index: 5950516 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.5469. Min Act: -0.1700
Data Index: 7212652 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.5156. Min Act: -0.1700
Data Index: 8417831 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.5156. Min Act: -0.1700
Data Index: 1382442 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8906. Min Range: -5.8906
Max Act: 5.5156. Min Act: -0.1700
Data Index: 1282056 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19