Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4982 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.9771. Min Act: -0.1700
Data Index: 2069712 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.9459. Min Act: -0.1700
Data Index: 682501 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.9146. Min Act: -0.1700
Data Index: 6559168 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.9146. Min Act: -0.1700
Data Index: 1899800 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.9459. Min Act: -0.1700
Data Index: 7074676 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.8521. Min Act: -0.1700
Data Index: 2565713 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.7896. Min Act: -0.1700
Data Index: 6831125 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.7584. Min Act: -0.1700
Data Index: 2865903 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.7271. Min Act: -0.1699
Data Index: 1788000 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.7271. Min Act: -0.1700
Data Index: 3482182 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.7271. Min Act: -0.1699
Data Index: 1811097 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.7271. Min Act: -0.1700
Data Index: 682502 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.7271. Min Act: -0.1700
Data Index: 250322 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.6646. Min Act: -0.1700
Data Index: 5575810 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.6646. Min Act: -0.1700
Data Index: 4114333 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.6334. Min Act: -0.1700
Data Index: 8559838 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.6646. Min Act: -0.1700
Data Index: 1053134 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.6334. Min Act: -0.1700
Data Index: 4131269 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.6334. Min Act: -0.1700
Data Index: 3473443 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9771. Min Range: -4.9771
Max Act: 4.6021. Min Act: -0.1700
Data Index: 2090289 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19