Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0742. Min Range: -6.0742
Max Act: 6.0742. Min Act: -0.1700
Data Index: 7802576 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0742. Min Range: -6.0742
Max Act: 6.0117. Min Act: -0.1700
Data Index: 2894262 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.9805. Min Act: -0.1700
Data Index: 3675344 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.9805. Min Act: -0.1700
Data Index: 7357883 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.9180. Min Act: -0.1700
Data Index: 8615832 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.9492. Min Act: -0.1700
Data Index: 234861 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.9180. Min Act: -0.1700
Data Index: 3789423 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.9492. Min Act: -0.1700
Data Index: 27434 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.9180. Min Act: -0.1700
Data Index: 1711975 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.8867. Min Act: -0.1700
Data Index: 6736089 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.8867. Min Act: -0.1700
Data Index: 6801832 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.8867. Min Act: -0.1700
Data Index: 3046310 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.8555. Min Act: -0.1700
Data Index: 6442515 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.8242. Min Act: -0.1700
Data Index: 4058870 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.8242. Min Act: -0.1700
Data Index: 3891532 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.7930. Min Act: -0.1700
Data Index: 5749698 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.8242. Min Act: -0.1700
Data Index: 7271087 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.7305. Min Act: -0.1700
Data Index: 7452654 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.6992. Min Act: -0.1700
Data Index: 2342940 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0742. Min Range: -6.0742
Max Act: 5.7305. Min Act: -0.1700
Data Index: 4537967 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19