Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4227 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3775. Min Range: -7.3775
Max Act: 7.3775. Min Act: -0.1700
Data Index: 7034675 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3775. Min Range: -7.3775
Max Act: 7.3463. Min Act: -0.1700
Data Index: 7266424 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3775. Min Range: -7.3775
Max Act: 7.3150. Min Act: -0.1700
Data Index: 200490 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3775. Min Range: -7.3775
Max Act: 7.2525. Min Act: -0.1700
Data Index: 3065770 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3775. Min Range: -7.3775
Max Act: 7.1900. Min Act: -0.1700
Data Index: 5818126 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3775. Min Range: -7.3775
Max Act: 7.1900. Min Act: -0.1700
Data Index: 1117338 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3775. Min Range: -7.3775
Max Act: 7.0963. Min Act: -0.1700
Data Index: 2988694 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3775. Min Range: -7.3775
Max Act: 7.0338. Min Act: -0.1700
Data Index: 7260946 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3775. Min Range: -7.3775
Max Act: 7.0650. Min Act: -0.1700
Data Index: 7094677 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3775. Min Range: -7.3775
Max Act: 7.0025. Min Act: -0.1700
Data Index: 7282025 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3775. Min Range: -7.3775
Max Act: 6.9713. Min Act: -0.1700
Data Index: 5459440 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3775. Min Range: -7.3775
Max Act: 6.9713. Min Act: -0.1700
Data Index: 398942 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3775. Min Range: -7.3775
Max Act: 6.9088. Min Act: -0.1700
Data Index: 3216395 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3775. Min Range: -7.3775
Max Act: 6.8463. Min Act: -0.1700
Data Index: 6636367 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3775. Min Range: -7.3775
Max Act: 6.8150. Min Act: -0.1700
Data Index: 7596576 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3775. Min Range: -7.3775
Max Act: 6.7838. Min Act: -0.1700
Data Index: 3505111 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3775. Min Range: -7.3775
Max Act: 6.7838. Min Act: -0.1700
Data Index: 6723056 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3775. Min Range: -7.3775
Max Act: 6.7525. Min Act: -0.1700
Data Index: 5243889 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3775. Min Range: -7.3775
Max Act: 6.7213. Min Act: -0.1700
Data Index: 7428673 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3775. Min Range: -7.3775
Max Act: 6.7213. Min Act: -0.1700
Data Index: 8221317 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19