Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2031 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.7778. Min Act: -0.1700
Data Index: 7146927 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.6841. Min Act: -0.1700
Data Index: 986453 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.6841. Min Act: -0.1700
Data Index: 4880025 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.6528. Min Act: -0.1700
Data Index: 5530429 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.6528. Min Act: -0.1700
Data Index: 4739607 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.5903. Min Act: -0.1700
Data Index: 8741843 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.5591. Min Act: -0.1700
Data Index: 8222896 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.5278. Min Act: -0.1700
Data Index: 252166 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.5278. Min Act: -0.1700
Data Index: 8423729 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.4966. Min Act: -0.1700
Data Index: 80680 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.4966. Min Act: -0.1700
Data Index: 3478531 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.4966. Min Act: -0.1700
Data Index: 479519 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.4653. Min Act: -0.1700
Data Index: 7046676 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.4653. Min Act: -0.1700
Data Index: 1590117 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.4653. Min Act: -0.1700
Data Index: 8003301 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.4341. Min Act: -0.1700
Data Index: 5345477 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.4028. Min Act: -0.1700
Data Index: 2884401 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.4028. Min Act: -0.1700
Data Index: 687902 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.4028. Min Act: -0.1700
Data Index: 2373454 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7778. Min Range: -5.7778
Max Act: 5.3403. Min Act: -0.1700
Data Index: 3925520 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19