Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 645 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.6448. Min Act: -0.1700
Data Index: 3122013 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.6361. Min Act: -0.1699
Data Index: 2771984 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.6187. Min Act: -0.1700
Data Index: 4459731 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.6099. Min Act: -0.1700
Data Index: 8772679 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.6187. Min Act: -0.1635
Data Index: 8589331 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.6187. Min Act: -0.1700
Data Index: 2652193 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.5925. Min Act: -0.1700
Data Index: 1810677 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.6012. Min Act: -0.1700
Data Index: 465379 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.6099. Min Act: -0.1700
Data Index: 8351502 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.6012. Min Act: -0.1700
Data Index: 7343760 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.6012. Min Act: -0.1700
Data Index: 2008076 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.5925. Min Act: -0.1695
Data Index: 1219052 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.5925. Min Act: -0.1700
Data Index: 8702571 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.5925. Min Act: -0.1700
Data Index: 3845816 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.5925. Min Act: -0.1692
Data Index: 7547064 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.5750. Min Act: -0.1700
Data Index: 8024791 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.5837. Min Act: -0.1700
Data Index: 1028026 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.5837. Min Act: -0.1699
Data Index: 850638 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.5837. Min Act: -0.1698
Data Index: 5915619 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6448. Min Range: -1.6448
Max Act: 1.5925. Min Act: -0.1700
Data Index: 681523 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19