Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3861. Min Range: -9.3861
Max Act: 9.3861. Min Act: -0.1700
Data Index: 5237289 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3861. Min Range: -9.3861
Max Act: 9.2611. Min Act: -0.1700
Data Index: 4848468 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3861. Min Range: -9.3861
Max Act: 9.1361. Min Act: -0.1700
Data Index: 6285438 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3861. Min Range: -9.3861
Max Act: 9.0736. Min Act: -0.1700
Data Index: 5037634 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3861. Min Range: -9.3861
Max Act: 9.0736. Min Act: -0.1700
Data Index: 7591137 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.9486. Min Act: -0.1700
Data Index: 2774644 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.8861. Min Act: -0.1700
Data Index: 3371193 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.9486. Min Act: -0.1700
Data Index: 520915 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.8236. Min Act: -0.1700
Data Index: 5037619 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.8236. Min Act: -0.1700
Data Index: 6999721 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.8236. Min Act: -0.1700
Data Index: 2030862 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.8236. Min Act: -0.1700
Data Index: 5237284 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.6986. Min Act: -0.1700
Data Index: 665204 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.7611. Min Act: -0.1700
Data Index: 8301128 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.7611. Min Act: -0.1700
Data Index: 4811837 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.6986. Min Act: -0.1700
Data Index: 4848473 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.6986. Min Act: -0.1700
Data Index: 7261071 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.6986. Min Act: -0.1700
Data Index: 4848480 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.7611. Min Act: -0.1700
Data Index: 5016915 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3861. Min Range: -9.3861
Max Act: 8.6361. Min Act: -0.1700
Data Index: 2577444 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19