Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2374 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4936. Min Range: -8.4936
Max Act: 8.4936. Min Act: -0.1700
Data Index: 7844747 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4936. Min Range: -8.4936
Max Act: 8.2436. Min Act: -0.1700
Data Index: 2781311 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4936. Min Range: -8.4936
Max Act: 8.0561. Min Act: -0.1700
Data Index: 7900535 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.9311. Min Act: -0.1700
Data Index: 4494870 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.8686. Min Act: -0.1700
Data Index: 8152193 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.8061. Min Act: -0.1700
Data Index: 2058582 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.8061. Min Act: -0.1700
Data Index: 1912830 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.8061. Min Act: -0.1700
Data Index: 998114 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.8061. Min Act: -0.1700
Data Index: 1172504 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.7436. Min Act: -0.1700
Data Index: 1382403 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.7436. Min Act: -0.1700
Data Index: 2697305 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.7436. Min Act: -0.1700
Data Index: 3269823 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.7436. Min Act: -0.1700
Data Index: 8216216 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.7436. Min Act: -0.1699
Data Index: 3034868 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.7436. Min Act: -0.1700
Data Index: 7379374 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.7436. Min Act: -0.1700
Data Index: 7596390 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.6186. Min Act: -0.1700
Data Index: 2565265 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.6811. Min Act: -0.1700
Data Index: 6520962 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.6811. Min Act: -0.1700
Data Index: 6639089 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4936. Min Range: -8.4936
Max Act: 7.6186. Min Act: -0.1700
Data Index: 3863954 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19