Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.5738. Min Act: -0.1700
Data Index: 5410651 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.4800. Min Act: -0.1700
Data Index: 5481404 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.4800. Min Act: -0.1700
Data Index: 2859589 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.4488. Min Act: -0.1700
Data Index: 2859590 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.4488. Min Act: -0.1700
Data Index: 4840167 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3550. Min Act: -0.1700
Data Index: 8159807 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3863. Min Act: -0.1700
Data Index: 484927 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3238. Min Act: -0.1700
Data Index: 663005 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2925. Min Act: -0.1700
Data Index: 4152001 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2925. Min Act: -0.1700
Data Index: 3472476 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3238. Min Act: -0.1700
Data Index: 1838670 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2925. Min Act: -0.1700
Data Index: 2634374 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3238. Min Act: -0.1700
Data Index: 5669613 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3238. Min Act: -0.1700
Data Index: 4629261 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2613. Min Act: -0.1700
Data Index: 4431325 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2300. Min Act: -0.1700
Data Index: 7437940 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2300. Min Act: -0.1700
Data Index: 592140 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2300. Min Act: -0.1700
Data Index: 6572187 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.1988. Min Act: -0.1700
Data Index: 7022523 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.1988. Min Act: -0.1700
Data Index: 4890834 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19