Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 296 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2818. Min Range: -7.2818
Max Act: 7.2818. Min Act: -0.1700
Data Index: 6144246 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2818. Min Range: -7.2818
Max Act: 7.1255. Min Act: -0.1700
Data Index: 2173611 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2818. Min Range: -7.2818
Max Act: 7.0005. Min Act: -0.1700
Data Index: 7530982 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.9693. Min Act: -0.1700
Data Index: 4969154 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.9380. Min Act: -0.1700
Data Index: 6297858 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.9068. Min Act: -0.1700
Data Index: 7963031 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.8130. Min Act: -0.1700
Data Index: 4282574 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.8130. Min Act: -0.1700
Data Index: 3026971 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.7818. Min Act: -0.1700
Data Index: 696462 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.7193. Min Act: -0.1700
Data Index: 7214155 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.7505. Min Act: -0.1700
Data Index: 4167274 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.7193. Min Act: -0.1700
Data Index: 663419 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.7193. Min Act: -0.1700
Data Index: 6528401 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.6568. Min Act: -0.1700
Data Index: 6767867 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.6880. Min Act: -0.1700
Data Index: 6390435 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.6568. Min Act: -0.1700
Data Index: 405960 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.6880. Min Act: -0.1700
Data Index: 3587963 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.5943. Min Act: -0.1700
Data Index: 1446213 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.5943. Min Act: -0.1700
Data Index: 3398212 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2818. Min Range: -7.2818
Max Act: 6.6255. Min Act: -0.1700
Data Index: 3466576 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19