Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4865 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.6766. Min Act: -0.1700
Data Index: 2532635 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.6454. Min Act: -0.1700
Data Index: 716008 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.6141. Min Act: -0.1700
Data Index: 289530 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.6141. Min Act: -0.1700
Data Index: 6997391 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5829. Min Act: -0.1700
Data Index: 100161 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5829. Min Act: -0.1700
Data Index: 3366696 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5516. Min Act: -0.1700
Data Index: 6170535 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5204. Min Act: -0.1700
Data Index: 6398822 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5204. Min Act: -0.1700
Data Index: 3084479 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5516. Min Act: -0.1700
Data Index: 3978367 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5829. Min Act: -0.1700
Data Index: 1729690 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5516. Min Act: -0.1700
Data Index: 4768109 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5204. Min Act: -0.1700
Data Index: 8094070 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5204. Min Act: -0.1700
Data Index: 3084482 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5204. Min Act: -0.1700
Data Index: 7414319 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5204. Min Act: -0.1700
Data Index: 8151990 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5204. Min Act: -0.1700
Data Index: 806434 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5204. Min Act: -0.1700
Data Index: 6707512 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.5204. Min Act: -0.1700
Data Index: 6316710 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6766. Min Range: -4.6766
Max Act: 4.4891. Min Act: -0.1700
Data Index: 7888626 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19