Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3258 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3484. Min Range: -10.3484
Max Act: 10.3484. Min Act: -0.1700
Data Index: 5558930 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3484. Min Range: -10.3484
Max Act: 10.0984. Min Act: -0.1700
Data Index: 8269314 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.5359. Min Act: -0.1700
Data Index: 7909817 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.4734. Min Act: -0.1700
Data Index: 4319838 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.4109. Min Act: -0.1700
Data Index: 5555048 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.4109. Min Act: -0.1700
Data Index: 1721927 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.4109. Min Act: -0.1700
Data Index: 6015495 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.3484. Min Act: -0.1700
Data Index: 1298318 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.3484. Min Act: -0.1700
Data Index: 6452631 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.2859. Min Act: -0.1700
Data Index: 7585383 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.2859. Min Act: -0.1700
Data Index: 1567519 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.2859. Min Act: -0.1700
Data Index: 7556945 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.2234. Min Act: -0.1700
Data Index: 2360289 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.2234. Min Act: -0.1700
Data Index: 6214072 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.2234. Min Act: -0.1700
Data Index: 482744 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.2234. Min Act: -0.1700
Data Index: 76227 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.2234. Min Act: -0.1700
Data Index: 7072490 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.1609. Min Act: -0.1700
Data Index: 1494657 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.1609. Min Act: -0.1700
Data Index: 6315212 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3484. Min Range: -10.3484
Max Act: 9.1609. Min Act: -0.1700
Data Index: 6788428 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19