Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3675 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2766. Min Range: -6.2766
Max Act: 6.2766. Min Act: -0.1700
Data Index: 7633368 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2766. Min Range: -6.2766
Max Act: 6.0579. Min Act: -0.1700
Data Index: 6334246 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.9329. Min Act: -0.1700
Data Index: 8154232 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.9329. Min Act: -0.1700
Data Index: 8166848 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.9016. Min Act: -0.1700
Data Index: 1604468 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.9016. Min Act: -0.1700
Data Index: 7913280 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.8704. Min Act: -0.1700
Data Index: 174351 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.8704. Min Act: -0.1700
Data Index: 2986840 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.8704. Min Act: -0.1700
Data Index: 8455687 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.8391. Min Act: -0.1700
Data Index: 8655646 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.8391. Min Act: -0.1700
Data Index: 1502695 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.8079. Min Act: -0.1700
Data Index: 8544238 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.8079. Min Act: -0.1700
Data Index: 4185195 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.8079. Min Act: -0.1700
Data Index: 8110407 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.8079. Min Act: -0.1700
Data Index: 7502632 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.7766. Min Act: -0.1700
Data Index: 1652937 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.7766. Min Act: -0.1700
Data Index: 959654 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.7766. Min Act: -0.1700
Data Index: 3075197 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.7766. Min Act: -0.1700
Data Index: 3160618 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2766. Min Range: -6.2766
Max Act: 5.7141. Min Act: -0.1700
Data Index: 6749853 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19