Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1961 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2328. Min Range: -8.2328
Max Act: 8.2328. Min Act: -0.1700
Data Index: 4119284 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.7328. Min Act: -0.1700
Data Index: 1548420 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.5766. Min Act: -0.1700
Data Index: 7951412 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.5766. Min Act: -0.1700
Data Index: 2846650 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.5453. Min Act: -0.1700
Data Index: 8179947 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.5141. Min Act: -0.1700
Data Index: 4895032 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.4203. Min Act: -0.1700
Data Index: 8694028 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.4203. Min Act: -0.1700
Data Index: 4847718 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.4203. Min Act: -0.1700
Data Index: 4675095 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.3891. Min Act: -0.1700
Data Index: 6263470 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.3578. Min Act: -0.1700
Data Index: 3462766 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.3266. Min Act: -0.1700
Data Index: 8822690 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.3578. Min Act: -0.1700
Data Index: 2691902 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.2953. Min Act: -0.1700
Data Index: 5791010 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.3266. Min Act: -0.1700
Data Index: 1216484 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.3266. Min Act: -0.1700
Data Index: 1677239 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.3266. Min Act: -0.1700
Data Index: 8800937 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.3266. Min Act: -0.1700
Data Index: 8152647 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.2953. Min Act: -0.1700
Data Index: 5825085 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2328. Min Range: -8.2328
Max Act: 7.2641. Min Act: -0.1700
Data Index: 436944 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19