Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3655 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7535. Min Range: -8.7535
Max Act: 8.7535. Min Act: -0.1700
Data Index: 4921850 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7535. Min Range: -8.7535
Max Act: 8.3473. Min Act: -0.1700
Data Index: 8573323 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7535. Min Range: -8.7535
Max Act: 8.2848. Min Act: -0.1700
Data Index: 5751849 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7535. Min Range: -8.7535
Max Act: 8.0973. Min Act: -0.1700
Data Index: 5350769 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7535. Min Range: -8.7535
Max Act: 8.0660. Min Act: -0.1700
Data Index: 795486 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.9723. Min Act: -0.1700
Data Index: 4203876 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.8785. Min Act: -0.1700
Data Index: 6003343 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.8785. Min Act: -0.1700
Data Index: 7959918 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.8785. Min Act: -0.1700
Data Index: 8046225 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.8473. Min Act: -0.1700
Data Index: 7555578 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.8160. Min Act: -0.1700
Data Index: 6179526 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.8473. Min Act: -0.1700
Data Index: 2308550 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.7848. Min Act: -0.1700
Data Index: 5445067 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.7535. Min Act: -0.1700
Data Index: 6767171 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.7535. Min Act: -0.1700
Data Index: 3861060 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.7535. Min Act: -0.1700
Data Index: 2977993 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.7535. Min Act: -0.1700
Data Index: 3212552 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.7535. Min Act: -0.1700
Data Index: 5913686 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.7223. Min Act: -0.1700
Data Index: 857624 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7535. Min Range: -8.7535
Max Act: 7.7535. Min Act: -0.1700
Data Index: 4949187 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19