Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4182 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.6516. Min Act: -0.1571
Data Index: 8600916 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.6516. Min Act: -0.1698
Data Index: 7136093 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.6356. Min Act: -0.1601
Data Index: 4468051 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.6195. Min Act: -0.1616
Data Index: 2331142 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.6195. Min Act: -0.1700
Data Index: 1059840 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5873. Min Act: -0.1700
Data Index: 5644428 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5873. Min Act: -0.1695
Data Index: 3114338 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5873. Min Act: -0.1281
Data Index: 8351671 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5712. Min Act: -0.1511
Data Index: 1168730 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5712. Min Act: -0.1700
Data Index: 1769679 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5873. Min Act: -0.1699
Data Index: 2199507 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5712. Min Act: -0.1688
Data Index: 7843475 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5551. Min Act: -0.1700
Data Index: 3088698 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5551. Min Act: -0.1438
Data Index: 396306 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5551. Min Act: -0.1659
Data Index: 6391695 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5228. Min Act: -0.1700
Data Index: 4712185 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5228. Min Act: -0.1605
Data Index: 1408147 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5228. Min Act: -0.1468
Data Index: 6132750 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5228. Min Act: -0.1691
Data Index: 2346334 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6516. Min Range: -2.6516
Max Act: 2.5228. Min Act: -0.1700
Data Index: 4615469 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19