Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5902 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.9905. Min Act: -0.1700
Data Index: 457092 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.8654. Min Act: -0.1700
Data Index: 1053538 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.8342. Min Act: -0.1700
Data Index: 1167680 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.7716. Min Act: -0.1700
Data Index: 2523983 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.7716. Min Act: -0.1700
Data Index: 4725530 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.8029. Min Act: -0.1700
Data Index: 4518678 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.7716. Min Act: -0.1700
Data Index: 4637013 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.7716. Min Act: -0.1700
Data Index: 5253202 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.7247. Min Act: -0.1700
Data Index: 691310 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.7403. Min Act: -0.1700
Data Index: 5101932 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.7247. Min Act: -0.1700
Data Index: 3585057 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.7247. Min Act: -0.1700
Data Index: 7454094 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.7247. Min Act: -0.1700
Data Index: 6707141 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.6934. Min Act: -0.1700
Data Index: 5935014 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.6934. Min Act: -0.1700
Data Index: 7540280 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.6934. Min Act: -0.1700
Data Index: 1893635 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.6778. Min Act: -0.1700
Data Index: 8665002 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.6621. Min Act: -0.1700
Data Index: 6707143 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.6621. Min Act: -0.1700
Data Index: 7139110 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9905. Min Range: -3.9905
Max Act: 3.6152. Min Act: -0.1700
Data Index: 6707142 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19