Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.7766. Min Act: -0.1700
Data Index: 3528370 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.7609. Min Act: -0.1700
Data Index: 6542117 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.7609. Min Act: -0.1700
Data Index: 8432756 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.7453. Min Act: -0.1700
Data Index: 3681388 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.6671. Min Act: -0.1700
Data Index: 4569102 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.6671. Min Act: -0.1700
Data Index: 1468978 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.5888. Min Act: -0.1700
Data Index: 6964016 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.5888. Min Act: -0.1700
Data Index: 968354 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.6045. Min Act: -0.1700
Data Index: 4562686 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.5575. Min Act: -0.1700
Data Index: 4354180 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.5419. Min Act: -0.1700
Data Index: 6678709 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.5262. Min Act: -0.1700
Data Index: 7918226 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.5262. Min Act: -0.1700
Data Index: 6336633 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.5262. Min Act: -0.1700
Data Index: 2747811 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.5105. Min Act: -0.1700
Data Index: 8531206 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.4792. Min Act: -0.1700
Data Index: 8664221 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.4636. Min Act: -0.1700
Data Index: 632746 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.4792. Min Act: -0.1700
Data Index: 3744936 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.4479. Min Act: -0.1700
Data Index: 8029246 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7766. Min Range: -3.7766
Max Act: 3.4479. Min Act: -0.1700
Data Index: 8459170 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19