Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 723 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5604. Min Range: -12.5604
Max Act: 12.5604. Min Act: -0.1700
Data Index: 6302528 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5604. Min Range: -12.5604
Max Act: 12.3104. Min Act: -0.1700
Data Index: 8018673 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5604. Min Range: -12.5604
Max Act: 12.2479. Min Act: -0.1700
Data Index: 777082 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5604. Min Range: -12.5604
Max Act: 12.1854. Min Act: -0.1700
Data Index: 5014361 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5604. Min Range: -12.5604
Max Act: 12.1854. Min Act: -0.1700
Data Index: 8572853 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5604. Min Range: -12.5604
Max Act: 12.1854. Min Act: -0.1700
Data Index: 5742371 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5604. Min Range: -12.5604
Max Act: 12.1229. Min Act: -0.1700
Data Index: 3212733 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5604. Min Range: -12.5604
Max Act: 12.0604. Min Act: -0.1700
Data Index: 2731387 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.9979. Min Act: -0.1700
Data Index: 7789923 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.8729. Min Act: -0.1700
Data Index: 4908821 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.9354. Min Act: -0.1700
Data Index: 6146495 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.8729. Min Act: -0.1700
Data Index: 3545511 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.8104. Min Act: -0.1700
Data Index: 7957880 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.8104. Min Act: -0.1700
Data Index: 6749626 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.8104. Min Act: -0.1700
Data Index: 3128777 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.8729. Min Act: -0.1700
Data Index: 6301429 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.8104. Min Act: -0.1700
Data Index: 7182927 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.8104. Min Act: -0.1700
Data Index: 5341642 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.7479. Min Act: -0.1700
Data Index: 1497739 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5604. Min Range: -12.5604
Max Act: 11.7479. Min Act: -0.1700
Data Index: 3445417 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19