Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1750 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.5541. Min Act: -0.1700
Data Index: 1721076 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.5541. Min Act: -0.1700
Data Index: 1282092 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.3353. Min Act: -0.1700
Data Index: 5832161 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.2728. Min Act: -0.1700
Data Index: 3655300 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.2728. Min Act: -0.1700
Data Index: 829227 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.2728. Min Act: -0.1700
Data Index: 1637402 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.2728. Min Act: -0.1700
Data Index: 7627271 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.2728. Min Act: -0.1700
Data Index: 6542362 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.1791. Min Act: -0.1700
Data Index: 3948026 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.2103. Min Act: -0.1700
Data Index: 2944716 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.1791. Min Act: -0.1700
Data Index: 4336888 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.1478. Min Act: -0.1700
Data Index: 7271422 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.1478. Min Act: -0.1700
Data Index: 2481448 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.1166. Min Act: -0.1700
Data Index: 2080756 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.1166. Min Act: -0.1700
Data Index: 8216039 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.1166. Min Act: -0.1700
Data Index: 7398100 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.1166. Min Act: -0.1700
Data Index: 6517911 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.0853. Min Act: -0.1700
Data Index: 4975932 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.0853. Min Act: -0.1700
Data Index: 2098837 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5541. Min Range: -4.5541
Max Act: 4.0853. Min Act: -0.1700
Data Index: 6693086 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19