Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4592 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0553. Min Range: -6.0553
Max Act: 6.0553. Min Act: -0.1700
Data Index: 6535720 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.9616. Min Act: -0.1700
Data Index: 7694450 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.8366. Min Act: -0.1700
Data Index: 2035626 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.6803. Min Act: -0.1700
Data Index: 6760353 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.6491. Min Act: -0.1700
Data Index: 7184816 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.6491. Min Act: -0.1700
Data Index: 8562600 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.6491. Min Act: -0.1700
Data Index: 3651048 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.5866. Min Act: -0.1700
Data Index: 8157615 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.5553. Min Act: -0.1700
Data Index: 3942648 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.5553. Min Act: -0.1700
Data Index: 2499146 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.5241. Min Act: -0.1700
Data Index: 5737781 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.5241. Min Act: -0.1700
Data Index: 4905477 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.5241. Min Act: -0.1700
Data Index: 2872409 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.5241. Min Act: -0.1700
Data Index: 8062987 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.5553. Min Act: -0.1700
Data Index: 7800099 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.4928. Min Act: -0.1700
Data Index: 6460793 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.4616. Min Act: -0.1700
Data Index: 2640405 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.4616. Min Act: -0.1700
Data Index: 1580186 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.4616. Min Act: -0.1700
Data Index: 6929684 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.4616. Min Act: -0.1700
Data Index: 1380183 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19