Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3880 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.5842. Min Act: -0.1373
Data Index: 1527127 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.3030. Min Act: -0.1700
Data Index: 6757305 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.3342. Min Act: -0.1697
Data Index: 4970920 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.3030. Min Act: -0.1699
Data Index: 6366507 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.2717. Min Act: -0.1699
Data Index: 8070619 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.2405. Min Act: -0.1697
Data Index: 373473 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.2092. Min Act: -0.1695
Data Index: 6757293 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.2092. Min Act: -0.1697
Data Index: 1676831 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1780. Min Act: -0.1697
Data Index: 5704802 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1467. Min Act: -0.1649
Data Index: 2731391 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1780. Min Act: -0.0608
Data Index: 1443521 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1467. Min Act: -0.1690
Data Index: 7005754 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1780. Min Act: -0.1700
Data Index: 2289733 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1780. Min Act: -0.1684
Data Index: 8367967 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1780. Min Act: -0.1693
Data Index: 5056215 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1780. Min Act: -0.1666
Data Index: 4415502 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1467. Min Act: -0.1669
Data Index: 1676709 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1780. Min Act: -0.1691
Data Index: 2680927 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1780. Min Act: -0.1683
Data Index: 5704803 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5842. Min Range: -6.5842
Max Act: 6.1780. Min Act: -0.1253
Data Index: 5056225 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19