Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3879 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.8724. Min Act: -0.1700
Data Index: 3555171 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.6224. Min Act: -0.1700
Data Index: 7862971 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.5599. Min Act: -0.1700
Data Index: 728360 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.5599. Min Act: -0.1700
Data Index: 8768109 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.5599. Min Act: -0.1700
Data Index: 99882 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.5286. Min Act: -0.1700
Data Index: 5838005 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.5286. Min Act: -0.1700
Data Index: 1024318 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4974. Min Act: -0.1700
Data Index: 3062102 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4661. Min Act: -0.1700
Data Index: 4496875 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4974. Min Act: -0.1700
Data Index: 2719231 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4661. Min Act: -0.1700
Data Index: 5807227 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4661. Min Act: -0.1700
Data Index: 6946012 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4661. Min Act: -0.1700
Data Index: 4527916 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4661. Min Act: -0.1700
Data Index: 5676253 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4349. Min Act: -0.1700
Data Index: 5909099 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4349. Min Act: -0.1700
Data Index: 6978490 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4036. Min Act: -0.1700
Data Index: 7710848 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4036. Min Act: -0.1700
Data Index: 2601456 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.4036. Min Act: -0.1700
Data Index: 2668533 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8724. Min Range: -7.8724
Max Act: 7.3724. Min Act: -0.1700
Data Index: 1915315 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19