Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4842 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.7013. Min Act: -0.1700
Data Index: 3418054 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.6075. Min Act: -0.1700
Data Index: 6379079 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.6075. Min Act: -0.1700
Data Index: 8111016 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.5763. Min Act: -0.1700
Data Index: 4597848 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.5763. Min Act: -0.1700
Data Index: 2000980 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.4825. Min Act: -0.1700
Data Index: 101677 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.4825. Min Act: -0.1700
Data Index: 4443148 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.4200. Min Act: -0.1700
Data Index: 2174706 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3888. Min Act: -0.1700
Data Index: 5340371 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3575. Min Act: -0.1700
Data Index: 6340043 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3888. Min Act: -0.1700
Data Index: 7587142 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3263. Min Act: -0.1700
Data Index: 2389064 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3263. Min Act: -0.1700
Data Index: 5478301 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3263. Min Act: -0.1700
Data Index: 5478302 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3263. Min Act: -0.1700
Data Index: 7693263 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3575. Min Act: -0.1700
Data Index: 7510096 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3263. Min Act: -0.1700
Data Index: 366365 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3263. Min Act: -0.1700
Data Index: 6764595 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3263. Min Act: -0.1700
Data Index: 2048215 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7013. Min Range: -4.7013
Max Act: 4.3263. Min Act: -0.1700
Data Index: 4001002 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19