Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 689 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.8447. Min Act: -0.1700
Data Index: 1953965 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.8135. Min Act: -0.1700
Data Index: 5316240 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.6885. Min Act: -0.1700
Data Index: 1162448 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.7822. Min Act: -0.1700
Data Index: 6262458 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.7197. Min Act: -0.1700
Data Index: 4037734 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.6572. Min Act: -0.1700
Data Index: 394504 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.5947. Min Act: -0.1700
Data Index: 6424950 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.6260. Min Act: -0.1700
Data Index: 3706334 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.5635. Min Act: -0.1700
Data Index: 1902523 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.6260. Min Act: -0.1700
Data Index: 8734906 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.6260. Min Act: -0.1700
Data Index: 8549646 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.5635. Min Act: -0.1700
Data Index: 2438416 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.4697. Min Act: -0.1700
Data Index: 1616766 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.4697. Min Act: -0.1700
Data Index: 5125626 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.4697. Min Act: -0.1700
Data Index: 5716269 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.5322. Min Act: -0.1700
Data Index: 4419169 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.4385. Min Act: -0.1700
Data Index: 6874941 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.4697. Min Act: -0.1700
Data Index: 2720751 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.5322. Min Act: -0.1700
Data Index: 3442052 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8447. Min Range: -5.8447
Max Act: 5.5322. Min Act: -0.1700
Data Index: 6967005 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19