Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.5412. Min Act: -0.1700
Data Index: 7337479 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.5099. Min Act: -0.1700
Data Index: 4711716 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.5099. Min Act: -0.1700
Data Index: 786593 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.4162. Min Act: -0.1700
Data Index: 5323296 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.3849. Min Act: -0.1700
Data Index: 1341042 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.3849. Min Act: -0.1700
Data Index: 1352173 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.3537. Min Act: -0.1700
Data Index: 364978 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.3224. Min Act: -0.1700
Data Index: 6168973 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.2287. Min Act: -0.1700
Data Index: 4252503 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.2599. Min Act: -0.1700
Data Index: 647394 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.1974. Min Act: -0.1700
Data Index: 6903929 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.2599. Min Act: -0.1700
Data Index: 7781253 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.1974. Min Act: -0.1700
Data Index: 3844548 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.2287. Min Act: -0.1700
Data Index: 2248001 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.1974. Min Act: -0.1700
Data Index: 7991443 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.1662. Min Act: -0.1700
Data Index: 4711718 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.1662. Min Act: -0.1700
Data Index: 6795387 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.1349. Min Act: -0.1700
Data Index: 2465996 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.1662. Min Act: -0.1700
Data Index: 1682468 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5412. Min Range: -5.5412
Max Act: 5.1662. Min Act: -0.1700
Data Index: 4134474 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19