Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.6538. Min Act: -0.1700
Data Index: 7288994 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.5913. Min Act: -0.1700
Data Index: 1821690 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4975. Min Act: -0.1700
Data Index: 5890577 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4975. Min Act: -0.1700
Data Index: 391690 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4663. Min Act: -0.1700
Data Index: 7594136 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4663. Min Act: -0.1700
Data Index: 7046011 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4350. Min Act: -0.1700
Data Index: 3677595 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4350. Min Act: -0.1700
Data Index: 5113224 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4350. Min Act: -0.1700
Data Index: 6730705 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4350. Min Act: -0.1700
Data Index: 4677567 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4350. Min Act: -0.1700
Data Index: 669797 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4350. Min Act: -0.1700
Data Index: 504136 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4038. Min Act: -0.1700
Data Index: 6826577 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4038. Min Act: -0.1700
Data Index: 500644 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.3725. Min Act: -0.1700
Data Index: 834732 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.3725. Min Act: -0.1700
Data Index: 769324 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.4038. Min Act: -0.1700
Data Index: 1860014 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.3725. Min Act: -0.1700
Data Index: 4356576 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.3725. Min Act: -0.1700
Data Index: 5395582 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6538. Min Range: -6.6538
Max Act: 6.3413. Min Act: -0.1700
Data Index: 3629329 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19