Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4236 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.4021. Min Act: -0.1700
Data Index: 8403075 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.3709. Min Act: -0.1700
Data Index: 2536206 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.2771. Min Act: -0.1700
Data Index: 4573755 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.2146. Min Act: -0.1700
Data Index: 1412804 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.1834. Min Act: -0.1700
Data Index: 9975 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.1834. Min Act: -0.1700
Data Index: 8150766 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.1521. Min Act: -0.1700
Data Index: 6350386 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.1209. Min Act: -0.1700
Data Index: 4030810 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.0896. Min Act: -0.1700
Data Index: 8382536 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.0584. Min Act: -0.1700
Data Index: 3071168 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.0584. Min Act: -0.1700
Data Index: 7436263 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.0584. Min Act: -0.1700
Data Index: 2932265 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.0271. Min Act: -0.1700
Data Index: 553347 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.0271. Min Act: -0.1700
Data Index: 4204618 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.0271. Min Act: -0.1700
Data Index: 3971392 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.0271. Min Act: -0.1700
Data Index: 280155 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4021. Min Range: -5.4021
Max Act: 5.0271. Min Act: -0.1700
Data Index: 8391145 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4021. Min Range: -5.4021
Max Act: 4.9959. Min Act: -0.1700
Data Index: 6852692 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4021. Min Range: -5.4021
Max Act: 4.9959. Min Act: -0.1700
Data Index: 6077718 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4021. Min Range: -5.4021
Max Act: 4.9646. Min Act: -0.1700
Data Index: 3869889 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19