Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 577 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.4544. Min Act: -0.1700
Data Index: 7808412 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.0794. Min Act: -0.1700
Data Index: 6506413 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.0481. Min Act: -0.1700
Data Index: 3582846 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.9856. Min Act: -0.1700
Data Index: 2262522 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.8919. Min Act: -0.1700
Data Index: 5876620 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.8919. Min Act: -0.1700
Data Index: 2793873 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.8606. Min Act: -0.1700
Data Index: 4044004 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.7981. Min Act: -0.1700
Data Index: 6102145 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.7669. Min Act: -0.1700
Data Index: 3743201 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.7356. Min Act: -0.1700
Data Index: 7533585 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.7356. Min Act: -0.1700
Data Index: 5616934 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.7356. Min Act: -0.1700
Data Index: 1734796 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.7044. Min Act: -0.1700
Data Index: 118155 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.7044. Min Act: -0.1700
Data Index: 747975 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.7044. Min Act: -0.1700
Data Index: 4189524 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.7044. Min Act: -0.1700
Data Index: 6839732 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.7356. Min Act: -0.1700
Data Index: 2308469 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.7044. Min Act: -0.1700
Data Index: 3947182 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.6419. Min Act: -0.1700
Data Index: 1943099 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.6419. Min Act: -0.1700
Data Index: 5781096 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19