Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 821 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3392. Min Range: -6.3392
Max Act: 6.3392. Min Act: -0.1700
Data Index: 6780796 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.9642. Min Act: -0.1700
Data Index: 4598194 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.9642. Min Act: -0.1700
Data Index: 2408731 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.8704. Min Act: -0.1700
Data Index: 7325604 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.8704. Min Act: -0.1700
Data Index: 4154623 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.8079. Min Act: -0.1700
Data Index: 5724856 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.7767. Min Act: -0.1700
Data Index: 7665984 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.7454. Min Act: -0.1700
Data Index: 5900493 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.7454. Min Act: -0.1700
Data Index: 1664063 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.7454. Min Act: -0.1700
Data Index: 3800807 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.7454. Min Act: -0.1700
Data Index: 8739839 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.7454. Min Act: -0.1700
Data Index: 4700699 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.7142. Min Act: -0.1700
Data Index: 4423406 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.7142. Min Act: -0.1700
Data Index: 7276152 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.7142. Min Act: -0.1700
Data Index: 350979 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.6829. Min Act: -0.1700
Data Index: 4913699 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.6517. Min Act: -0.1700
Data Index: 2398541 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.6204. Min Act: -0.1700
Data Index: 4468679 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.6204. Min Act: -0.1700
Data Index: 5534473 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3392. Min Range: -6.3392
Max Act: 5.6204. Min Act: -0.1700
Data Index: 4297900 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19