Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2549 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.6424. Min Act: -0.1673
Data Index: 8813738 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.5814. Min Act: -0.1559
Data Index: 6103106 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.5639. Min Act: -0.1630
Data Index: 681728 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.5201. Min Act: -0.1698
Data Index: 5642976 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.5201. Min Act: -0.1700
Data Index: 2110477 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.5201. Min Act: -0.1611
Data Index: 3764540 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.5025. Min Act: -0.1508
Data Index: 1256790 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4849. Min Act: -0.1699
Data Index: 7516618 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4849. Min Act: -0.1687
Data Index: 1514067 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4849. Min Act: -0.1696
Data Index: 6853942 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4849. Min Act: -0.1651
Data Index: 1702366 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4762. Min Act: -0.1677
Data Index: 1635885 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4674. Min Act: -0.1620
Data Index: 6141615 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4762. Min Act: -0.1616
Data Index: 6151851 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4849. Min Act: -0.1601
Data Index: 4036970 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4674. Min Act: -0.1698
Data Index: 1396380 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4849. Min Act: -0.1696
Data Index: 6340077 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4586. Min Act: -0.1666
Data Index: 8075730 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4674. Min Act: -0.1688
Data Index: 419193 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6424. Min Range: -1.6424
Max Act: 1.4498. Min Act: -0.1664
Data Index: 6065078 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19