Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.7398. Min Act: -0.1700
Data Index: 2035751 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.6148. Min Act: -0.1700
Data Index: 5442103 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.6148. Min Act: -0.1700
Data Index: 1129639 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.6148. Min Act: -0.1700
Data Index: 345719 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.6148. Min Act: -0.1700
Data Index: 2410508 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.5836. Min Act: -0.1700
Data Index: 5038233 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.5836. Min Act: -0.1700
Data Index: 4399002 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.5523. Min Act: -0.1700
Data Index: 4772703 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.5836. Min Act: -0.1700
Data Index: 68866 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.5523. Min Act: -0.1700
Data Index: 436172 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.5211. Min Act: -0.1700
Data Index: 791957 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.5211. Min Act: -0.1700
Data Index: 6970717 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.5211. Min Act: -0.1700
Data Index: 3490842 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.5211. Min Act: -0.1700
Data Index: 6578041 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.5211. Min Act: -0.1700
Data Index: 3711338 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.4898. Min Act: -0.1700
Data Index: 8315998 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.4898. Min Act: -0.1700
Data Index: 2672414 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.4586. Min Act: -0.1700
Data Index: 8702818 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.4586. Min Act: -0.1700
Data Index: 3537265 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7398. Min Range: -6.7398
Max Act: 6.4273. Min Act: -0.1700
Data Index: 1528674 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19