Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1146 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.8005. Min Act: -0.1700
Data Index: 6049132 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.6442. Min Act: -0.1700
Data Index: 4755669 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.6442. Min Act: -0.1700
Data Index: 5580376 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.5817. Min Act: -0.1700
Data Index: 6142928 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.6442. Min Act: -0.1700
Data Index: 4435643 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.5817. Min Act: -0.1700
Data Index: 8692731 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.5505. Min Act: -0.1700
Data Index: 3117392 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.5817. Min Act: -0.1700
Data Index: 420432 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.5192. Min Act: -0.1700
Data Index: 3467298 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.5192. Min Act: -0.1700
Data Index: 2822318 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.5192. Min Act: -0.1700
Data Index: 420438 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.4880. Min Act: -0.1700
Data Index: 5560934 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.4880. Min Act: -0.1700
Data Index: 4444926 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.4880. Min Act: -0.1700
Data Index: 1642553 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.4880. Min Act: -0.1700
Data Index: 2713618 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.4880. Min Act: -0.1700
Data Index: 2099879 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.4255. Min Act: -0.1700
Data Index: 7151975 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.4567. Min Act: -0.1700
Data Index: 3200664 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.4255. Min Act: -0.1700
Data Index: 8678189 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8005. Min Range: -4.8005
Max Act: 4.4255. Min Act: -0.1700
Data Index: 6599229 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19