Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2046 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.9503. Min Act: -0.1700
Data Index: 4439260 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.6691. Min Act: -0.1700
Data Index: 1440825 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.6378. Min Act: -0.1700
Data Index: 5189600 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.6066. Min Act: -0.1700
Data Index: 6765672 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.5753. Min Act: -0.1700
Data Index: 6425246 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.5441. Min Act: -0.1700
Data Index: 898883 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.5441. Min Act: -0.1700
Data Index: 832856 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.5128. Min Act: -0.1700
Data Index: 7539702 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.5128. Min Act: -0.1700
Data Index: 4114875 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.4816. Min Act: -0.1700
Data Index: 476274 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.4503. Min Act: -0.1700
Data Index: 1849176 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.4191. Min Act: -0.1700
Data Index: 4405849 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.4191. Min Act: -0.1700
Data Index: 8820829 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.3566. Min Act: -0.1700
Data Index: 4405851 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.3878. Min Act: -0.1700
Data Index: 5260023 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.3253. Min Act: -0.1700
Data Index: 4168174 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.3878. Min Act: -0.1700
Data Index: 4149760 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.3253. Min Act: -0.1700
Data Index: 6657833 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.2941. Min Act: -0.1700
Data Index: 5902196 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9503. Min Range: -4.9503
Max Act: 4.2941. Min Act: -0.1700
Data Index: 4787473 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19