Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.5954. Min Act: -0.1700
Data Index: 3790466 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.5329. Min Act: -0.1700
Data Index: 5079212 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.4079. Min Act: -0.1700
Data Index: 2425526 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.3454. Min Act: -0.1700
Data Index: 6275960 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.3766. Min Act: -0.1700
Data Index: 2157284 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.3454. Min Act: -0.1700
Data Index: 2388521 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.3141. Min Act: -0.1700
Data Index: 2424455 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.3141. Min Act: -0.1700
Data Index: 1488792 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.2829. Min Act: -0.1700
Data Index: 5853591 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.2829. Min Act: -0.1700
Data Index: 7681541 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.2204. Min Act: -0.1700
Data Index: 1279158 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.1891. Min Act: -0.1700
Data Index: 5381913 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.1579. Min Act: -0.1700
Data Index: 3500610 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.1579. Min Act: -0.1700
Data Index: 2114566 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.0954. Min Act: -0.1700
Data Index: 6538081 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.0641. Min Act: -0.1700
Data Index: 7847566 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.0641. Min Act: -0.1700
Data Index: 5455613 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5954. Min Range: -6.5954
Max Act: 6.0016. Min Act: -0.1700
Data Index: 7069922 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5954. Min Range: -6.5954
Max Act: 5.9704. Min Act: -0.1700
Data Index: 1731710 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5954. Min Range: -6.5954
Max Act: 5.9704. Min Act: -0.1700
Data Index: 4360281 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19