Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1754 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.6595. Min Act: -0.1700
Data Index: 5790504 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.6283. Min Act: -0.1700
Data Index: 2149694 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.5970. Min Act: -0.1700
Data Index: 5611824 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.5658. Min Act: -0.1700
Data Index: 2724988 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.5345. Min Act: -0.1700
Data Index: 979013 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.5658. Min Act: -0.1700
Data Index: 4180282 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.5345. Min Act: -0.1700
Data Index: 4320355 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.4720. Min Act: -0.1700
Data Index: 2663686 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.4720. Min Act: -0.1700
Data Index: 1724836 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.4720. Min Act: -0.1700
Data Index: 4114808 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.4408. Min Act: -0.1700
Data Index: 7263942 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.4095. Min Act: -0.1700
Data Index: 7020101 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.3158. Min Act: -0.1700
Data Index: 69545 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.3470. Min Act: -0.1700
Data Index: 2676122 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.2845. Min Act: -0.1700
Data Index: 2238263 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.3158. Min Act: -0.1700
Data Index: 4607562 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.2845. Min Act: -0.1700
Data Index: 4987682 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.2533. Min Act: -0.1700
Data Index: 2557445 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.2533. Min Act: -0.1700
Data Index: 4878501 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6595. Min Range: -6.6595
Max Act: 6.2220. Min Act: -0.1700
Data Index: 1701077 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19