Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6398 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1868. Min Range: -10.1868
Max Act: 10.1868. Min Act: -0.1700
Data Index: 3495698 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.9368. Min Act: -0.1700
Data Index: 5716520 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.8118. Min Act: -0.1700
Data Index: 1089137 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.8118. Min Act: -0.1700
Data Index: 3818870 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.7493. Min Act: -0.1700
Data Index: 2496668 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.7493. Min Act: -0.1700
Data Index: 7197579 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.7493. Min Act: -0.1700
Data Index: 4057947 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.6243. Min Act: -0.1700
Data Index: 1169392 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.7493. Min Act: -0.1700
Data Index: 3401670 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.6868. Min Act: -0.1700
Data Index: 5332819 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.6243. Min Act: -0.1700
Data Index: 3087282 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.6243. Min Act: -0.1700
Data Index: 5325080 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.6243. Min Act: -0.1700
Data Index: 4985777 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.6243. Min Act: -0.1700
Data Index: 1591570 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.6243. Min Act: -0.1700
Data Index: 1567616 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.6243. Min Act: -0.1700
Data Index: 8034272 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.5618. Min Act: -0.1700
Data Index: 530377 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.5618. Min Act: -0.1700
Data Index: 3656743 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.5618. Min Act: -0.1700
Data Index: 3479954 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1868. Min Range: -10.1868
Max Act: 9.5618. Min Act: -0.1700
Data Index: 666382 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19