Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1822 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3834. Min Range: -5.3834
Max Act: 5.3834. Min Act: -0.1700
Data Index: 5338942 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3834. Min Range: -5.3834
Max Act: 5.3209. Min Act: -0.1700
Data Index: 1732893 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3834. Min Range: -5.3834
Max Act: 5.3209. Min Act: -0.1700
Data Index: 330328 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3834. Min Range: -5.3834
Max Act: 5.2897. Min Act: -0.1700
Data Index: 2762705 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3834. Min Range: -5.3834
Max Act: 5.2897. Min Act: -0.1700
Data Index: 6571247 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3834. Min Range: -5.3834
Max Act: 5.1959. Min Act: -0.1700
Data Index: 7855755 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3834. Min Range: -5.3834
Max Act: 5.0709. Min Act: -0.1700
Data Index: 5982641 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3834. Min Range: -5.3834
Max Act: 5.0397. Min Act: -0.1700
Data Index: 5731850 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3834. Min Range: -5.3834
Max Act: 5.0084. Min Act: -0.1700
Data Index: 4828863 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3834. Min Range: -5.3834
Max Act: 4.9459. Min Act: -0.1700
Data Index: 6714182 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3834. Min Range: -5.3834
Max Act: 4.9459. Min Act: -0.1700
Data Index: 7846541 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3834. Min Range: -5.3834
Max Act: 4.8834. Min Act: -0.1700
Data Index: 4403691 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3834. Min Range: -5.3834
Max Act: 4.8834. Min Act: -0.1700
Data Index: 4546523 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3834. Min Range: -5.3834
Max Act: 4.9147. Min Act: -0.1700
Data Index: 459832 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3834. Min Range: -5.3834
Max Act: 4.8834. Min Act: -0.1700
Data Index: 1504122 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3834. Min Range: -5.3834
Max Act: 4.8834. Min Act: -0.1700
Data Index: 2352877 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3834. Min Range: -5.3834
Max Act: 4.8834. Min Act: -0.1700
Data Index: 1781038 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3834. Min Range: -5.3834
Max Act: 4.8834. Min Act: -0.1700
Data Index: 4362443 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3834. Min Range: -5.3834
Max Act: 4.8522. Min Act: -0.1700
Data Index: 6660321 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3834. Min Range: -5.3834
Max Act: 4.8522. Min Act: -0.1700
Data Index: 6965155 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19