Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2680 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1703. Min Range: -6.1703
Max Act: 6.1703. Min Act: -0.1700
Data Index: 8546843 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1703. Min Range: -6.1703
Max Act: 6.1703. Min Act: -0.1700
Data Index: 7994636 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1703. Min Range: -6.1703
Max Act: 6.1390. Min Act: -0.1700
Data Index: 1665336 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1703. Min Range: -6.1703
Max Act: 6.0765. Min Act: -0.1700
Data Index: 2968654 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.9828. Min Act: -0.1700
Data Index: 57466 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1703. Min Range: -6.1703
Max Act: 6.0140. Min Act: -0.1700
Data Index: 3505252 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.9828. Min Act: -0.1700
Data Index: 8375814 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.9515. Min Act: -0.1700
Data Index: 2834039 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.9203. Min Act: -0.1700
Data Index: 954476 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.8578. Min Act: -0.1700
Data Index: 6492756 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.8578. Min Act: -0.1700
Data Index: 1080714 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.8578. Min Act: -0.1700
Data Index: 2387340 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.7953. Min Act: -0.1700
Data Index: 4119706 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.7640. Min Act: -0.1700
Data Index: 4320720 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.7640. Min Act: -0.1700
Data Index: 3409675 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.7328. Min Act: -0.1700
Data Index: 3293877 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.7328. Min Act: -0.1700
Data Index: 5244332 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.7015. Min Act: -0.1700
Data Index: 4750615 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.6703. Min Act: -0.1700
Data Index: 8509657 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1703. Min Range: -6.1703
Max Act: 5.6703. Min Act: -0.1700
Data Index: 6547959 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19