Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5344 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.4959. Min Act: -0.1700
Data Index: 8003966 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.4959. Min Act: -0.1700
Data Index: 2465455 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.3709. Min Act: -0.1700
Data Index: 11909 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.3084. Min Act: -0.1700
Data Index: 2365281 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.3084. Min Act: -0.1700
Data Index: 5958850 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.3084. Min Act: -0.1700
Data Index: 7239979 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.2771. Min Act: -0.1700
Data Index: 3792300 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.1209. Min Act: -0.1700
Data Index: 6546751 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.1209. Min Act: -0.1700
Data Index: 5456195 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.1209. Min Act: -0.1700
Data Index: 2864010 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.0896. Min Act: -0.1700
Data Index: 4515891 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.0584. Min Act: -0.1700
Data Index: 7608332 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.0584. Min Act: -0.1700
Data Index: 3998413 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.0584. Min Act: -0.1700
Data Index: 456365 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.0584. Min Act: -0.1700
Data Index: 1267614 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4959. Min Range: -6.4959
Max Act: 5.9959. Min Act: -0.1700
Data Index: 5970536 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.0271. Min Act: -0.1700
Data Index: 5868447 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.0271. Min Act: -0.1700
Data Index: 8399541 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4959. Min Range: -6.4959
Max Act: 5.9959. Min Act: -0.1696
Data Index: 2082786 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4959. Min Range: -6.4959
Max Act: 6.0271. Min Act: -0.1695
Data Index: 2452570 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19