Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.2592. Min Act: -0.1700
Data Index: 4040129 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.2592. Min Act: -0.1700
Data Index: 2693111 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.2280. Min Act: -0.1700
Data Index: 1325178 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.2280. Min Act: -0.1700
Data Index: 4089892 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.2280. Min Act: -0.1700
Data Index: 4731069 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.2280. Min Act: -0.1700
Data Index: 7062415 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.1030. Min Act: -0.1700
Data Index: 3524538 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.0717. Min Act: -0.1700
Data Index: 6438899 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.0717. Min Act: -0.1700
Data Index: 646551 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.0405. Min Act: -0.1700
Data Index: 8504307 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.0092. Min Act: -0.1700
Data Index: 2062916 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.0092. Min Act: -0.1700
Data Index: 8414432 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2592. Min Range: -5.2592
Max Act: 5.0092. Min Act: -0.1700
Data Index: 6016114 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2592. Min Range: -5.2592
Max Act: 4.9780. Min Act: -0.1700
Data Index: 1436370 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2592. Min Range: -5.2592
Max Act: 4.9467. Min Act: -0.1700
Data Index: 1167922 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2592. Min Range: -5.2592
Max Act: 4.9780. Min Act: -0.1700
Data Index: 1325171 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2592. Min Range: -5.2592
Max Act: 4.9155. Min Act: -0.1700
Data Index: 3830164 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2592. Min Range: -5.2592
Max Act: 4.9467. Min Act: -0.1700
Data Index: 1271306 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2592. Min Range: -5.2592
Max Act: 4.9467. Min Act: -0.1700
Data Index: 2049128 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2592. Min Range: -5.2592
Max Act: 4.9155. Min Act: -0.1700
Data Index: 1983912 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19