Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2107 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.3897. Min Act: -0.1700
Data Index: 2216556 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.2959. Min Act: -0.1700
Data Index: 4885532 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.2334. Min Act: -0.1700
Data Index: 449886 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.2334. Min Act: -0.1700
Data Index: 3729655 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.2022. Min Act: -0.1700
Data Index: 7421393 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.1709. Min Act: -0.1700
Data Index: 6348779 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.1397. Min Act: -0.1700
Data Index: 6078695 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.0772. Min Act: -0.1700
Data Index: 5092840 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.1084. Min Act: -0.1700
Data Index: 5952093 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.0772. Min Act: -0.1700
Data Index: 2968296 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.0772. Min Act: -0.1700
Data Index: 2601699 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.0459. Min Act: -0.1700
Data Index: 7597428 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.0459. Min Act: -0.1700
Data Index: 6875897 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.0772. Min Act: -0.1700
Data Index: 3345760 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.0147. Min Act: -0.1700
Data Index: 8282986 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.0459. Min Act: -0.1700
Data Index: 6219759 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3897. Min Range: -6.3897
Max Act: 6.0459. Min Act: -0.1700
Data Index: 2714057 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3897. Min Range: -6.3897
Max Act: 5.9834. Min Act: -0.1700
Data Index: 2842741 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3897. Min Range: -6.3897
Max Act: 5.9522. Min Act: -0.1700
Data Index: 6138521 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3897. Min Range: -6.3897
Max Act: 5.9522. Min Act: -0.1700
Data Index: 1606330 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19