Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1064 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.7273. Min Act: -0.1696
Data Index: 4562644 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.6648. Min Act: -0.1700
Data Index: 7447345 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.6023. Min Act: -0.1700
Data Index: 7447355 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.5398. Min Act: -0.1698
Data Index: 4562646 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.4148. Min Act: -0.1696
Data Index: 6883427 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.4148. Min Act: -0.1699
Data Index: 7447325 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.3523. Min Act: -0.1700
Data Index: 7165286 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.3523. Min Act: -0.1700
Data Index: 4562645 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.2898. Min Act: -0.1700
Data Index: 7447324 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.2898. Min Act: -0.1700
Data Index: 7447348 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.2898. Min Act: -0.1699
Data Index: 7447323 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.2898. Min Act: -0.1699
Data Index: 7447334 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.2898. Min Act: -0.1699
Data Index: 7447343 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.2898. Min Act: -0.1700
Data Index: 1311641 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.2273. Min Act: -0.1700
Data Index: 7447332 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.1648. Min Act: -0.1699
Data Index: 4562643 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.1648. Min Act: -0.1700
Data Index: 7447336 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.1648. Min Act: -0.1700
Data Index: 7447327 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.1648. Min Act: -0.1700
Data Index: 7447337 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7273. Min Range: -11.7273
Max Act: 11.1648. Min Act: -0.1700
Data Index: 7447352 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19