Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 73 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.3439. Min Act: -0.1700
Data Index: 3282171 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.3439. Min Act: -0.1700
Data Index: 6012773 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.3127. Min Act: -0.1700
Data Index: 3282170 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.2814. Min Act: -0.1700
Data Index: 8332441 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.2189. Min Act: -0.1700
Data Index: 6012774 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.2502. Min Act: -0.1700
Data Index: 3282169 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.1877. Min Act: -0.1700
Data Index: 8775584 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.1564. Min Act: -0.1700
Data Index: 3282168 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.1564. Min Act: -0.1700
Data Index: 3282172 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.1564. Min Act: -0.1700
Data Index: 6012777 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.1564. Min Act: -0.1700
Data Index: 8775583 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.1564. Min Act: -0.1700
Data Index: 6012775 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.1252. Min Act: -0.1700
Data Index: 6012776 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.1252. Min Act: -0.1700
Data Index: 8118385 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.1252. Min Act: -0.1700
Data Index: 8775585 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.0627. Min Act: -0.1700
Data Index: 6012772 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.0627. Min Act: -0.1700
Data Index: 8543025 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.0314. Min Act: -0.1700
Data Index: 7976196 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.0314. Min Act: -0.1700
Data Index: 5907986 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3439. Min Range: -7.3439
Max Act: 7.0627. Min Act: -0.1700
Data Index: 581024 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19