Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 945 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1416. Min Range: -6.1416
Max Act: 6.1416. Min Act: -0.1700
Data Index: 8484827 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1416. Min Range: -6.1416
Max Act: 6.0478. Min Act: -0.1700
Data Index: 356047 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.9541. Min Act: -0.1700
Data Index: 4109016 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.9228. Min Act: -0.1700
Data Index: 4342531 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.8916. Min Act: -0.1700
Data Index: 4845969 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.8603. Min Act: -0.1700
Data Index: 5150272 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.8291. Min Act: -0.1700
Data Index: 7292789 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.8291. Min Act: -0.1700
Data Index: 4173852 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.7666. Min Act: -0.1700
Data Index: 6626009 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.7666. Min Act: -0.1700
Data Index: 3734810 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.7978. Min Act: -0.1700
Data Index: 5145105 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.7353. Min Act: -0.1700
Data Index: 3619550 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.7353. Min Act: -0.1700
Data Index: 377691 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.7353. Min Act: -0.1700
Data Index: 2770440 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.7353. Min Act: -0.1700
Data Index: 5310361 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.7353. Min Act: -0.1700
Data Index: 1149126 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.7353. Min Act: -0.1700
Data Index: 419996 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.7666. Min Act: -0.1700
Data Index: 2114138 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.7041. Min Act: -0.1700
Data Index: 139897 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1416. Min Range: -6.1416
Max Act: 5.6728. Min Act: -0.1700
Data Index: 6159832 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19