Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 504 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.5005. Min Act: -0.1700
Data Index: 2448481 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.4693. Min Act: -0.1700
Data Index: 6276163 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.3755. Min Act: -0.1700
Data Index: 3458893 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.2818. Min Act: -0.1700
Data Index: 1943399 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.2505. Min Act: -0.1700
Data Index: 5245635 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.2193. Min Act: -0.1700
Data Index: 2022873 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.2193. Min Act: -0.1700
Data Index: 3641120 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.2193. Min Act: -0.1700
Data Index: 336006 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.2193. Min Act: -0.1700
Data Index: 2126692 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.2193. Min Act: -0.1700
Data Index: 5603449 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.2193. Min Act: -0.1700
Data Index: 4877450 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1880. Min Act: -0.1700
Data Index: 4524872 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1880. Min Act: -0.1700
Data Index: 2906530 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1880. Min Act: -0.1700
Data Index: 7944013 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.2193. Min Act: -0.1700
Data Index: 4831083 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1880. Min Act: -0.1700
Data Index: 4121279 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1568. Min Act: -0.1700
Data Index: 3528558 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1255. Min Act: -0.1700
Data Index: 5829793 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1568. Min Act: -0.1700
Data Index: 7282257 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1255. Min Act: -0.1700
Data Index: 6438159 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19