Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2828 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.4395. Min Act: -0.1700
Data Index: 1452557 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.3743. Min Act: -0.1700
Data Index: 4496828 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.3743. Min Act: -0.1700
Data Index: 7607334 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.3415. Min Act: -0.1700
Data Index: 1993873 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.3743. Min Act: -0.1700
Data Index: 3864526 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.3415. Min Act: -0.1700
Data Index: 8088831 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.3251. Min Act: -0.1700
Data Index: 574605 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.3251. Min Act: -0.1700
Data Index: 463465 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.3251. Min Act: -0.1700
Data Index: 7452745 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.2923. Min Act: -0.1700
Data Index: 7568058 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.2923. Min Act: -0.1700
Data Index: 5703694 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.2758. Min Act: -0.1700
Data Index: 7938056 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.2923. Min Act: -0.1700
Data Index: 6457993 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.2923. Min Act: -0.1700
Data Index: 7022950 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.2923. Min Act: -0.1700
Data Index: 3067633 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.2593. Min Act: -0.1700
Data Index: 6435659 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.2593. Min Act: -0.1700
Data Index: 8500185 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.2428. Min Act: -0.1700
Data Index: 4191627 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.2428. Min Act: -0.1700
Data Index: 7662537 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4395. Min Range: -2.4395
Max Act: 2.2428. Min Act: -0.1700
Data Index: 6005238 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19