Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 807 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.7677. Min Act: -0.1700
Data Index: 1139701 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.7677. Min Act: -0.1700
Data Index: 8394724 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.7677. Min Act: -0.1700
Data Index: 16197 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.7677. Min Act: -0.1700
Data Index: 1064425 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.7364. Min Act: -0.1700
Data Index: 4843611 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6739. Min Act: -0.1700
Data Index: 4355350 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.7052. Min Act: -0.1700
Data Index: 8328101 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.7052. Min Act: -0.1700
Data Index: 6504378 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.7052. Min Act: -0.1700
Data Index: 107556 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6739. Min Act: -0.1700
Data Index: 2475005 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6739. Min Act: -0.1700
Data Index: 5593893 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6427. Min Act: -0.1700
Data Index: 4355349 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6427. Min Act: -0.1700
Data Index: 2983459 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6427. Min Act: -0.1699
Data Index: 1559658 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6427. Min Act: -0.1700
Data Index: 7941456 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6427. Min Act: -0.1700
Data Index: 680929 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6427. Min Act: -0.1700
Data Index: 3712469 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6427. Min Act: -0.1700
Data Index: 6594347 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6739. Min Act: -0.1700
Data Index: 4141798 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6427. Min Act: -0.1700
Data Index: 8359839 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19