Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1786 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.3554. Min Act: -0.1700
Data Index: 6894934 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.3242. Min Act: -0.1700
Data Index: 7034103 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.2929. Min Act: -0.1700
Data Index: 555810 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.2929. Min Act: -0.1700
Data Index: 4242233 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.2617. Min Act: -0.1700
Data Index: 2964474 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.1992. Min Act: -0.1700
Data Index: 6675426 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.1992. Min Act: -0.1700
Data Index: 5794035 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.1679. Min Act: -0.1700
Data Index: 7441813 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.1679. Min Act: -0.1700
Data Index: 7746111 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.1054. Min Act: -0.1700
Data Index: 5949449 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.0741. Min Act: -0.1700
Data Index: 6977795 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.0429. Min Act: -0.1700
Data Index: 7862776 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.0429. Min Act: -0.1700
Data Index: 7930322 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3554. Min Range: -4.3554
Max Act: 4.0429. Min Act: -0.1700
Data Index: 2362523 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3554. Min Range: -4.3554
Max Act: 3.9804. Min Act: -0.1700
Data Index: 6736234 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3554. Min Range: -4.3554
Max Act: 3.9804. Min Act: -0.1700
Data Index: 8113677 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3554. Min Range: -4.3554
Max Act: 3.9804. Min Act: -0.1700
Data Index: 2515330 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3554. Min Range: -4.3554
Max Act: 3.9491. Min Act: -0.1700
Data Index: 1418504 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3554. Min Range: -4.3554
Max Act: 3.9491. Min Act: -0.1700
Data Index: 3073051 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3554. Min Range: -4.3554
Max Act: 3.9178. Min Act: -0.1700
Data Index: 2845903 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19