Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1854 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.3697. Min Act: -0.1700
Data Index: 8552926 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.3697. Min Act: -0.1700
Data Index: 4487899 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.2912. Min Act: -0.1700
Data Index: 1403187 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.2441. Min Act: -0.1700
Data Index: 1600025 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.2441. Min Act: -0.1700
Data Index: 5559989 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.2912. Min Act: -0.1700
Data Index: 3610808 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.2127. Min Act: -0.1700
Data Index: 6484655 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.2127. Min Act: -0.1700
Data Index: 7925356 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.1969. Min Act: -0.1700
Data Index: 2759753 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.1812. Min Act: -0.1700
Data Index: 3743426 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.2284. Min Act: -0.1700
Data Index: 804627 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.1812. Min Act: -0.1700
Data Index: 552474 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.1812. Min Act: -0.1700
Data Index: 7016637 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.1655. Min Act: -0.1700
Data Index: 646321 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.1812. Min Act: -0.1700
Data Index: 1434816 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.1655. Min Act: -0.1700
Data Index: 8073912 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.1497. Min Act: -0.1700
Data Index: 1497966 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.1497. Min Act: -0.1700
Data Index: 4979289 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.1497. Min Act: -0.1700
Data Index: 2865752 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3697. Min Range: -3.3697
Max Act: 3.1497. Min Act: -0.1700
Data Index: 3610908 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19