Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4572 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.9398. Min Act: -0.1700
Data Index: 5799328 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.9085. Min Act: -0.1700
Data Index: 190291 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.8460. Min Act: -0.1700
Data Index: 5061015 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.8148. Min Act: -0.1700
Data Index: 7045763 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.6898. Min Act: -0.1700
Data Index: 634527 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.5960. Min Act: -0.1700
Data Index: 6401095 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.5648. Min Act: -0.1700
Data Index: 6661786 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.5023. Min Act: -0.1700
Data Index: 2899052 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4710. Min Act: -0.1700
Data Index: 7620796 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4710. Min Act: -0.1700
Data Index: 7710390 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4710. Min Act: -0.1700
Data Index: 1806586 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4398. Min Act: -0.1700
Data Index: 4547080 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4398. Min Act: -0.1700
Data Index: 7888550 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4398. Min Act: -0.1700
Data Index: 1749101 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4085. Min Act: -0.1700
Data Index: 608278 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.3773. Min Act: -0.1700
Data Index: 39776 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.3773. Min Act: -0.1700
Data Index: 539458 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.3460. Min Act: -0.1700
Data Index: 3684654 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.3773. Min Act: -0.1700
Data Index: 556983 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.3460. Min Act: -0.1700
Data Index: 8811889 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19