Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4990. Min Range: -8.4990
Max Act: 8.4990. Min Act: -0.1700
Data Index: 3503762 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4990. Min Range: -8.4990
Max Act: 8.4990. Min Act: -0.1700
Data Index: 7563642 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4990. Min Range: -8.4990
Max Act: 8.4990. Min Act: -0.1700
Data Index: 8352765 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4990. Min Range: -8.4990
Max Act: 8.4365. Min Act: -0.1700
Data Index: 5336665 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4990. Min Range: -8.4990
Max Act: 8.2178. Min Act: -0.1700
Data Index: 5526832 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4990. Min Range: -8.4990
Max Act: 8.1865. Min Act: -0.1700
Data Index: 6387430 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4990. Min Range: -8.4990
Max Act: 8.1865. Min Act: -0.1700
Data Index: 2139868 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4990. Min Range: -8.4990
Max Act: 8.2178. Min Act: -0.1700
Data Index: 3632939 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4990. Min Range: -8.4990
Max Act: 8.1240. Min Act: -0.1700
Data Index: 7300989 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.9990. Min Act: -0.1700
Data Index: 5612763 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.9990. Min Act: -0.1700
Data Index: 8461823 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.9990. Min Act: -0.1700
Data Index: 981812 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.9678. Min Act: -0.1700
Data Index: 2748262 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.9678. Min Act: -0.1700
Data Index: 3704326 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.9365. Min Act: -0.1700
Data Index: 8461818 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.9053. Min Act: -0.1700
Data Index: 24937 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.8740. Min Act: -0.1700
Data Index: 5584770 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.8740. Min Act: -0.1700
Data Index: 4403462 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.8428. Min Act: -0.1700
Data Index: 4614939 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.7803. Min Act: -0.1700
Data Index: 3428736 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19