Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6376 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.5666. Min Act: -0.1700
Data Index: 335100 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.4728. Min Act: -0.1700
Data Index: 8375087 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.3478. Min Act: -0.1700
Data Index: 5033137 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.2541. Min Act: -0.1700
Data Index: 4578106 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.2228. Min Act: -0.1700
Data Index: 3081010 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.1916. Min Act: -0.1700
Data Index: 37712 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.1916. Min Act: -0.1700
Data Index: 1554827 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.1603. Min Act: -0.1700
Data Index: 7757684 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.1916. Min Act: -0.1700
Data Index: 6332505 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.1603. Min Act: -0.1700
Data Index: 8370004 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.1603. Min Act: -0.1700
Data Index: 3558354 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.1603. Min Act: -0.1700
Data Index: 7325769 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.1916. Min Act: -0.1700
Data Index: 922903 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.0978. Min Act: -0.1700
Data Index: 3656501 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.0978. Min Act: -0.1700
Data Index: 4163996 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.0978. Min Act: -0.1700
Data Index: 2452586 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.0978. Min Act: -0.1700
Data Index: 3739547 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.0666. Min Act: -0.1700
Data Index: 7303113 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.0666. Min Act: -0.1700
Data Index: 7666477 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5666. Min Range: -7.5666
Max Act: 7.0666. Min Act: -0.1700
Data Index: 1449214 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19