Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.4476. Min Act: -0.1700
Data Index: 8379218 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.3226. Min Act: -0.1700
Data Index: 6882120 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.3539. Min Act: -0.1700
Data Index: 1004831 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.3539. Min Act: -0.1700
Data Index: 4649109 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.2601. Min Act: -0.1700
Data Index: 7388164 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.2289. Min Act: -0.1700
Data Index: 1473112 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.1664. Min Act: -0.1700
Data Index: 3684311 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.1976. Min Act: -0.1700
Data Index: 7762244 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.1351. Min Act: -0.1700
Data Index: 5922935 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.1351. Min Act: -0.1700
Data Index: 4898879 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.1351. Min Act: -0.1700
Data Index: 6505672 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.1039. Min Act: -0.1700
Data Index: 2385485 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.1039. Min Act: -0.1700
Data Index: 2520052 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.1039. Min Act: -0.1700
Data Index: 4120332 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.1039. Min Act: -0.1700
Data Index: 655161 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.1039. Min Act: -0.1700
Data Index: 5327474 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.1039. Min Act: -0.1700
Data Index: 7077513 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.0726. Min Act: -0.1700
Data Index: 6562443 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.0726. Min Act: -0.1700
Data Index: 4303855 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4476. Min Range: -5.4476
Max Act: 5.0726. Min Act: -0.1700
Data Index: 5544561 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19