Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2759 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.7563. Min Act: -0.1700
Data Index: 1885605 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.6626. Min Act: -0.1700
Data Index: 188003 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.5063. Min Act: -0.1700
Data Index: 1265709 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.5063. Min Act: -0.1700
Data Index: 6687406 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.4751. Min Act: -0.1700
Data Index: 8206689 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.4438. Min Act: -0.1700
Data Index: 2688591 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.4126. Min Act: -0.1700
Data Index: 6464592 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.3813. Min Act: -0.1700
Data Index: 5335728 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.3501. Min Act: -0.1700
Data Index: 546760 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.3188. Min Act: -0.1700
Data Index: 5013534 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.2876. Min Act: -0.1700
Data Index: 3004082 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.2876. Min Act: -0.1700
Data Index: 3459234 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.3188. Min Act: -0.1700
Data Index: 7016896 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.2876. Min Act: -0.1700
Data Index: 1004884 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.2251. Min Act: -0.1700
Data Index: 4212722 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.2251. Min Act: -0.1700
Data Index: 6176957 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.1938. Min Act: -0.1700
Data Index: 5679228 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.1938. Min Act: -0.1700
Data Index: 4560448 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.1626. Min Act: -0.1700
Data Index: 7023461 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.1626. Min Act: -0.1700
Data Index: 6841684 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19