Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3866 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.7973. Min Act: -0.1700
Data Index: 5609291 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.7348. Min Act: -0.1700
Data Index: 2138421 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.7973. Min Act: -0.1700
Data Index: 762202 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.7348. Min Act: -0.1700
Data Index: 2411383 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.7348. Min Act: -0.1700
Data Index: 5466446 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6723. Min Act: -0.1700
Data Index: 4766732 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6723. Min Act: -0.1700
Data Index: 2583780 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6098. Min Act: -0.1700
Data Index: 3394812 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6723. Min Act: -0.1700
Data Index: 1223288 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6723. Min Act: -0.1700
Data Index: 1320024 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6098. Min Act: -0.1700
Data Index: 7666342 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6723. Min Act: -0.1700
Data Index: 5177659 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6098. Min Act: -0.1700
Data Index: 8520637 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6723. Min Act: -0.1700
Data Index: 715054 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6723. Min Act: -0.1700
Data Index: 3268149 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6098. Min Act: -0.1700
Data Index: 2483927 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.6098. Min Act: -0.1700
Data Index: 2147250 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.5473. Min Act: -0.1700
Data Index: 8453846 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.4848. Min Act: -0.1700
Data Index: 6363119 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7973. Min Range: -8.7973
Max Act: 8.5473. Min Act: -0.1700
Data Index: 5574961 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19