Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.6834. Min Act: -0.1700
Data Index: 2281993 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.6834. Min Act: -0.1700
Data Index: 2149429 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.6209. Min Act: -0.1700
Data Index: 6952987 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.5584. Min Act: -0.1700
Data Index: 8662764 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.5584. Min Act: -0.1700
Data Index: 7070698 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.5584. Min Act: -0.1700
Data Index: 3907310 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.5272. Min Act: -0.1700
Data Index: 8471441 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.5272. Min Act: -0.1700
Data Index: 4719412 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.4959. Min Act: -0.1700
Data Index: 5557013 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.4959. Min Act: -0.1700
Data Index: 70919 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.4647. Min Act: -0.1700
Data Index: 4719411 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.4334. Min Act: -0.1700
Data Index: 4892371 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.4022. Min Act: -0.1700
Data Index: 7070707 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.4022. Min Act: -0.1700
Data Index: 6681805 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.4022. Min Act: -0.1700
Data Index: 5214877 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.3397. Min Act: -0.1700
Data Index: 5557012 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.3709. Min Act: -0.1700
Data Index: 1190133 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.3709. Min Act: -0.1700
Data Index: 1076966 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.3709. Min Act: -0.1700
Data Index: 7788228 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6834. Min Range: -5.6834
Max Act: 5.3709. Min Act: -0.1700
Data Index: 4221855 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19