Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5047 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.8813. Min Act: -0.1700
Data Index: 4672833 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.8501. Min Act: -0.1700
Data Index: 1838125 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.8188. Min Act: -0.1700
Data Index: 430121 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.7876. Min Act: -0.1700
Data Index: 1838123 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.7876. Min Act: -0.1700
Data Index: 2553427 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.7563. Min Act: -0.1700
Data Index: 147561 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.7563. Min Act: -0.1700
Data Index: 3604044 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.7563. Min Act: -0.1700
Data Index: 430120 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.7251. Min Act: -0.1700
Data Index: 8660360 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.7251. Min Act: -0.1700
Data Index: 823899 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.7251. Min Act: -0.1700
Data Index: 859773 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.7251. Min Act: -0.1700
Data Index: 5623008 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.6626. Min Act: -0.1700
Data Index: 3866554 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.6938. Min Act: -0.1700
Data Index: 5244058 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.6626. Min Act: -0.1700
Data Index: 1215759 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.6313. Min Act: -0.1700
Data Index: 22280 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.6626. Min Act: -0.1700
Data Index: 8247116 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.6626. Min Act: -0.1700
Data Index: 1291993 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.6313. Min Act: -0.1700
Data Index: 1381096 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8813. Min Range: -4.8813
Max Act: 4.6313. Min Act: -0.1700
Data Index: 7662410 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19