Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2837. Min Act: -0.1700
Data Index: 5682271 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2507. Min Act: -0.1699
Data Index: 7316664 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2507. Min Act: -0.1700
Data Index: 1402992 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2341. Min Act: -0.1700
Data Index: 5828078 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2507. Min Act: -0.1700
Data Index: 6046830 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2341. Min Act: -0.1700
Data Index: 7020440 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2176. Min Act: -0.1700
Data Index: 443857 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2176. Min Act: -0.1700
Data Index: 8764357 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2010. Min Act: -0.1700
Data Index: 6544589 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2176. Min Act: -0.1700
Data Index: 6241117 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2010. Min Act: -0.1700
Data Index: 7748195 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2176. Min Act: -0.1699
Data Index: 1688580 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.1844. Min Act: -0.1700
Data Index: 8416522 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.1844. Min Act: -0.1700
Data Index: 5974637 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.1844. Min Act: -0.1694
Data Index: 6754339 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.1844. Min Act: -0.1700
Data Index: 6015838 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.2010. Min Act: -0.1700
Data Index: 2441674 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.1678. Min Act: -0.1700
Data Index: 597531 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.1678. Min Act: -0.1700
Data Index: 4616735 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2837. Min Range: -2.2837
Max Act: 2.1678. Min Act: -0.1700
Data Index: 2462031 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19