Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 595 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.8396. Min Act: -0.1700
Data Index: 6909197 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.7302. Min Act: -0.1700
Data Index: 5973791 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6207. Min Act: -0.1700
Data Index: 1747129 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6363. Min Act: -0.1700
Data Index: 3804194 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6050. Min Act: -0.1700
Data Index: 4967818 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6050. Min Act: -0.1700
Data Index: 3899793 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5580. Min Act: -0.1700
Data Index: 2397719 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5737. Min Act: -0.1700
Data Index: 3737674 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5894. Min Act: -0.1700
Data Index: 1253292 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5580. Min Act: -0.1700
Data Index: 8197700 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5737. Min Act: -0.1700
Data Index: 7922862 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5580. Min Act: -0.1700
Data Index: 7475467 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5580. Min Act: -0.1700
Data Index: 6709769 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5267. Min Act: -0.1700
Data Index: 181314 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5267. Min Act: -0.1700
Data Index: 7626111 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5424. Min Act: -0.1700
Data Index: 7868422 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5111. Min Act: -0.1700
Data Index: 1993282 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5111. Min Act: -0.1700
Data Index: 4554111 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.5111. Min Act: -0.1700
Data Index: 4774138 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.4954. Min Act: -0.1700
Data Index: 4231642 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19