Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2085 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4885. Min Range: -7.4885
Max Act: 7.4885. Min Act: -0.1700
Data Index: 5632014 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4885. Min Range: -7.4885
Max Act: 7.2073. Min Act: -0.1700
Data Index: 1804286 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4885. Min Range: -7.4885
Max Act: 7.0510. Min Act: -0.1700
Data Index: 3554147 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4885. Min Range: -7.4885
Max Act: 7.1135. Min Act: -0.1700
Data Index: 5129272 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.9885. Min Act: -0.1700
Data Index: 5421255 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.8323. Min Act: -0.1700
Data Index: 3547155 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.8323. Min Act: -0.1700
Data Index: 8625848 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.8010. Min Act: -0.1700
Data Index: 2260253 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.8010. Min Act: -0.1700
Data Index: 6979376 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.7698. Min Act: -0.1700
Data Index: 8154469 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.8010. Min Act: -0.1700
Data Index: 2047516 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.7698. Min Act: -0.1700
Data Index: 2055607 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.7385. Min Act: -0.1700
Data Index: 3889997 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.7698. Min Act: -0.1700
Data Index: 347664 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.7698. Min Act: -0.1700
Data Index: 4239733 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.7073. Min Act: -0.1700
Data Index: 7081644 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.7385. Min Act: -0.1700
Data Index: 895775 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.7073. Min Act: -0.1700
Data Index: 782632 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.7073. Min Act: -0.1700
Data Index: 143575 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4885. Min Range: -7.4885
Max Act: 6.6448. Min Act: -0.1700
Data Index: 7826879 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19