Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5057 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0329. Min Range: -7.0329
Max Act: 7.0329. Min Act: -0.1700
Data Index: 3627426 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.9704. Min Act: -0.1700
Data Index: 3442006 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.9704. Min Act: -0.1700
Data Index: 699536 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.9391. Min Act: -0.1700
Data Index: 36105 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.8454. Min Act: -0.1700
Data Index: 1920419 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.8454. Min Act: -0.1700
Data Index: 6854400 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.7829. Min Act: -0.1700
Data Index: 5674020 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.7516. Min Act: -0.1700
Data Index: 303845 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.7516. Min Act: -0.1700
Data Index: 7440262 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.7204. Min Act: -0.1700
Data Index: 8594115 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.7204. Min Act: -0.1700
Data Index: 5625599 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.6579. Min Act: -0.1700
Data Index: 3170517 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.6579. Min Act: -0.1700
Data Index: 1435979 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.6579. Min Act: -0.1700
Data Index: 7769328 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.6579. Min Act: -0.1700
Data Index: 7358054 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.6579. Min Act: -0.1700
Data Index: 4091273 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.5954. Min Act: -0.1700
Data Index: 2586357 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.5641. Min Act: -0.1700
Data Index: 6383822 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.5641. Min Act: -0.1700
Data Index: 4096625 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0329. Min Range: -7.0329
Max Act: 6.5641. Min Act: -0.1700
Data Index: 4264638 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19