Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1707 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.7251. Min Act: -0.1700
Data Index: 7471975 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.6626. Min Act: -0.1700
Data Index: 3392664 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.5688. Min Act: -0.1698
Data Index: 2677945 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.5063. Min Act: -0.1700
Data Index: 339233 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.4438. Min Act: -0.1700
Data Index: 8821182 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.4751. Min Act: -0.1700
Data Index: 4999826 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.4438. Min Act: -0.1700
Data Index: 5077590 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.4438. Min Act: -0.1700
Data Index: 1644767 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.4126. Min Act: -0.1700
Data Index: 1812138 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.3813. Min Act: -0.1700
Data Index: 2412799 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.3813. Min Act: -0.1700
Data Index: 4992704 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.3813. Min Act: -0.1700
Data Index: 899561 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.3813. Min Act: -0.1700
Data Index: 4675513 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.3501. Min Act: -0.1700
Data Index: 6668419 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.3501. Min Act: -0.1700
Data Index: 8041533 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.3188. Min Act: -0.1700
Data Index: 4745756 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.2876. Min Act: -0.1700
Data Index: 6676968 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.3188. Min Act: -0.1700
Data Index: 5288232 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.3188. Min Act: -0.1700
Data Index: 7578206 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7251. Min Range: -6.7251
Max Act: 6.2876. Min Act: -0.1700
Data Index: 1280253 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19