Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5838 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.8096. Min Act: -0.1700
Data Index: 8075794 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.7159. Min Act: -0.1700
Data Index: 363694 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.6534. Min Act: -0.1700
Data Index: 5009227 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.6534. Min Act: -0.1700
Data Index: 1675102 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.6221. Min Act: -0.1700
Data Index: 7263947 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.6221. Min Act: -0.1700
Data Index: 5749794 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.6221. Min Act: -0.1700
Data Index: 2914503 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.6221. Min Act: -0.1700
Data Index: 4323383 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.6221. Min Act: -0.1700
Data Index: 2516305 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.5909. Min Act: -0.1700
Data Index: 4359976 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.5909. Min Act: -0.1700
Data Index: 2409941 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.5596. Min Act: -0.1700
Data Index: 4985299 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.5596. Min Act: -0.1700
Data Index: 8336405 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.5596. Min Act: -0.1700
Data Index: 6931561 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.5596. Min Act: -0.1700
Data Index: 6302471 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.5596. Min Act: -0.1700
Data Index: 4267780 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.5596. Min Act: -0.1700
Data Index: 6214785 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.5596. Min Act: -0.1700
Data Index: 5840060 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.5596. Min Act: -0.1700
Data Index: 5467277 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8096. Min Range: -4.8096
Max Act: 4.5284. Min Act: -0.1700
Data Index: 4759508 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19