Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1308. Min Range: -6.1308
Max Act: 6.1308. Min Act: -0.1700
Data Index: 5336684 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1308. Min Range: -6.1308
Max Act: 6.0683. Min Act: -0.1700
Data Index: 4339647 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1308. Min Range: -6.1308
Max Act: 6.0058. Min Act: -0.1700
Data Index: 3236722 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.9746. Min Act: -0.1700
Data Index: 7903756 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.8496. Min Act: -0.1700
Data Index: 7282065 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.8183. Min Act: -0.1700
Data Index: 3493473 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.8496. Min Act: -0.1700
Data Index: 2431336 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.8183. Min Act: -0.1700
Data Index: 2795457 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.7871. Min Act: -0.1700
Data Index: 8140432 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.7246. Min Act: -0.1700
Data Index: 5569854 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.6621. Min Act: -0.1700
Data Index: 8427524 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.6308. Min Act: -0.1700
Data Index: 7823130 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.5996. Min Act: -0.1700
Data Index: 7048579 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.5996. Min Act: -0.1700
Data Index: 8422676 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.5996. Min Act: -0.1700
Data Index: 4317905 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.5683. Min Act: -0.1700
Data Index: 2026967 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.5371. Min Act: -0.1700
Data Index: 2154046 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.5371. Min Act: -0.1700
Data Index: 8275328 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.4746. Min Act: -0.1700
Data Index: 4298624 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1308. Min Range: -6.1308
Max Act: 5.4433. Min Act: -0.1700
Data Index: 7272970 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19