Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 246 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7989. Min Range: -6.7989
Max Act: 6.7989. Min Act: -0.1700
Data Index: 806503 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7989. Min Range: -6.7989
Max Act: 6.4551. Min Act: -0.1700
Data Index: 7871815 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7989. Min Range: -6.7989
Max Act: 6.3301. Min Act: -0.1700
Data Index: 6595516 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7989. Min Range: -6.7989
Max Act: 6.2364. Min Act: -0.1700
Data Index: 7373313 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7989. Min Range: -6.7989
Max Act: 6.1426. Min Act: -0.1700
Data Index: 5512707 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7989. Min Range: -6.7989
Max Act: 6.0801. Min Act: -0.1700
Data Index: 3110069 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7989. Min Range: -6.7989
Max Act: 6.0489. Min Act: -0.1700
Data Index: 4299694 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7989. Min Range: -6.7989
Max Act: 6.0176. Min Act: -0.1700
Data Index: 3385229 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.9864. Min Act: -0.1700
Data Index: 3953134 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.9864. Min Act: -0.1700
Data Index: 6990887 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.9864. Min Act: -0.1700
Data Index: 7544265 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.9864. Min Act: -0.1700
Data Index: 374004 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.9239. Min Act: -0.1700
Data Index: 7334025 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.9864. Min Act: -0.1700
Data Index: 5292438 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.9239. Min Act: -0.1700
Data Index: 6712808 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.9551. Min Act: -0.1700
Data Index: 3177594 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.8926. Min Act: -0.1700
Data Index: 1140766 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.9239. Min Act: -0.1700
Data Index: 3574877 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.9239. Min Act: -0.1700
Data Index: 1919691 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7989. Min Range: -6.7989
Max Act: 5.8926. Min Act: -0.1700
Data Index: 1489908 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19