Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5254 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2409. Min Range: -7.2409
Max Act: 7.2409. Min Act: -0.1700
Data Index: 7187911 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.8346. Min Act: -0.1700
Data Index: 3150415 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.7096. Min Act: -0.1700
Data Index: 912524 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.6159. Min Act: -0.1700
Data Index: 7187910 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.5846. Min Act: -0.1700
Data Index: 7187909 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.5846. Min Act: -0.1700
Data Index: 1508675 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.5534. Min Act: -0.1700
Data Index: 912525 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.5534. Min Act: -0.1700
Data Index: 1787532 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.4909. Min Act: -0.1700
Data Index: 4669350 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.5221. Min Act: -0.1700
Data Index: 8208660 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.5221. Min Act: -0.1700
Data Index: 6827656 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.3971. Min Act: -0.1700
Data Index: 5657663 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.3971. Min Act: -0.1700
Data Index: 4906800 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.3971. Min Act: -0.1700
Data Index: 657233 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.3659. Min Act: -0.1700
Data Index: 7187912 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.3659. Min Act: -0.1700
Data Index: 6774067 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.3346. Min Act: -0.1700
Data Index: 3644519 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.3346. Min Act: -0.1700
Data Index: 3864530 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.3346. Min Act: -0.1700
Data Index: 6141237 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2409. Min Range: -7.2409
Max Act: 6.3346. Min Act: -0.1700
Data Index: 480596 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19