Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.4738. Min Act: -0.1700
Data Index: 7850081 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.0050. Min Act: -0.1700
Data Index: 4205203 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.9425. Min Act: -0.1700
Data Index: 6120469 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.9425. Min Act: -0.1700
Data Index: 5885007 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.8488. Min Act: -0.1700
Data Index: 4238061 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.8175. Min Act: -0.1700
Data Index: 5381824 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.7863. Min Act: -0.1700
Data Index: 6288856 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.7238. Min Act: -0.1700
Data Index: 3230640 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.7238. Min Act: -0.1700
Data Index: 5758777 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.7238. Min Act: -0.1700
Data Index: 3708079 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.6925. Min Act: -0.1700
Data Index: 6146105 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.6925. Min Act: -0.1700
Data Index: 1583768 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.6925. Min Act: -0.1700
Data Index: 463338 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.6613. Min Act: -0.1700
Data Index: 3271912 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.6613. Min Act: -0.1700
Data Index: 51162 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.5988. Min Act: -0.1700
Data Index: 1267145 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.5988. Min Act: -0.1700
Data Index: 348893 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.5363. Min Act: -0.1700
Data Index: 4520897 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.5675. Min Act: -0.1700
Data Index: 5606215 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4738. Min Range: -6.4738
Max Act: 5.5675. Min Act: -0.1700
Data Index: 4837928 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19