Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.9757. Min Act: -0.1700
Data Index: 1774035 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.9445. Min Act: -0.1700
Data Index: 1774032 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.9445. Min Act: -0.1700
Data Index: 6174902 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.9445. Min Act: -0.1700
Data Index: 5586766 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.9132. Min Act: -0.1700
Data Index: 4063241 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.8820. Min Act: -0.1700
Data Index: 2590273 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.8507. Min Act: -0.1700
Data Index: 6380212 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.8507. Min Act: -0.1696
Data Index: 2639780 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.8507. Min Act: -0.1700
Data Index: 8645864 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.8507. Min Act: -0.1700
Data Index: 6095319 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.8195. Min Act: -0.1700
Data Index: 4053309 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.8195. Min Act: -0.1700
Data Index: 8769704 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.8195. Min Act: -0.1700
Data Index: 1386872 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.8195. Min Act: -0.1700
Data Index: 7290611 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.8195. Min Act: -0.1698
Data Index: 8025618 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.8195. Min Act: -0.1700
Data Index: 8634482 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.7882. Min Act: -0.1699
Data Index: 6866438 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.7882. Min Act: -0.1700
Data Index: 6920587 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.7882. Min Act: -0.1700
Data Index: 7106835 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9757. Min Range: -4.9757
Max Act: 4.7882. Min Act: -0.1700
Data Index: 8016697 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19