Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5470 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8019. Min Range: -6.8019
Max Act: 6.8019. Min Act: -0.1700
Data Index: 2324630 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8019. Min Range: -6.8019
Max Act: 6.2707. Min Act: -0.1700
Data Index: 6586564 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8019. Min Range: -6.8019
Max Act: 6.3019. Min Act: -0.1700
Data Index: 3921135 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8019. Min Range: -6.8019
Max Act: 6.1457. Min Act: -0.1700
Data Index: 7931654 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8019. Min Range: -6.8019
Max Act: 6.1769. Min Act: -0.1700
Data Index: 319713 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8019. Min Range: -6.8019
Max Act: 6.1144. Min Act: -0.1700
Data Index: 5686153 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8019. Min Range: -6.8019
Max Act: 6.0832. Min Act: -0.1700
Data Index: 6756067 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.9894. Min Act: -0.1700
Data Index: 8641976 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8019. Min Range: -6.8019
Max Act: 6.0207. Min Act: -0.1700
Data Index: 942727 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.9894. Min Act: -0.1700
Data Index: 5543246 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.9582. Min Act: -0.1700
Data Index: 4788991 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.9582. Min Act: -0.1700
Data Index: 3714589 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.9582. Min Act: -0.1700
Data Index: 2619816 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.9582. Min Act: -0.1700
Data Index: 1214302 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.9269. Min Act: -0.1700
Data Index: 7205299 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.8957. Min Act: -0.1700
Data Index: 353216 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.8957. Min Act: -0.1700
Data Index: 2309359 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.8957. Min Act: -0.1700
Data Index: 6482529 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.8957. Min Act: -0.1700
Data Index: 571389 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8019. Min Range: -6.8019
Max Act: 5.8644. Min Act: -0.1700
Data Index: 5073708 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19