Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6084. Min Range: -7.6084
Max Act: 7.6084. Min Act: -0.1700
Data Index: 2299307 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6084. Min Range: -7.6084
Max Act: 7.5772. Min Act: -0.1700
Data Index: 3420163 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6084. Min Range: -7.6084
Max Act: 7.2959. Min Act: -0.1700
Data Index: 8772867 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6084. Min Range: -7.6084
Max Act: 7.1709. Min Act: -0.1700
Data Index: 8031479 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6084. Min Range: -7.6084
Max Act: 7.0772. Min Act: -0.1700
Data Index: 3095806 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6084. Min Range: -7.6084
Max Act: 7.0459. Min Act: -0.1700
Data Index: 3351763 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6084. Min Range: -7.6084
Max Act: 7.0459. Min Act: -0.1700
Data Index: 4091179 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.9209. Min Act: -0.1700
Data Index: 7604839 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.9209. Min Act: -0.1700
Data Index: 158830 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.8584. Min Act: -0.1700
Data Index: 2006822 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.8272. Min Act: -0.1700
Data Index: 4266758 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.8272. Min Act: -0.1700
Data Index: 51514 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.8272. Min Act: -0.1700
Data Index: 7427263 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.7647. Min Act: -0.1700
Data Index: 7040271 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.7334. Min Act: -0.1700
Data Index: 6083184 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.6709. Min Act: -0.1700
Data Index: 5717228 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.6397. Min Act: -0.1700
Data Index: 7980758 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.6397. Min Act: -0.1700
Data Index: 3663688 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.6397. Min Act: -0.1700
Data Index: 7820130 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6084. Min Range: -7.6084
Max Act: 6.6397. Min Act: -0.1700
Data Index: 6548157 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19