Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.6180. Min Act: -0.1700
Data Index: 7829535 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.5212. Min Act: -0.1700
Data Index: 1217691 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.5050. Min Act: -0.1700
Data Index: 7851444 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4888. Min Act: -0.1700
Data Index: 6648195 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4888. Min Act: -0.1700
Data Index: 1905391 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4726. Min Act: -0.1700
Data Index: 5267957 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4726. Min Act: -0.1700
Data Index: 587863 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4564. Min Act: -0.1700
Data Index: 2119624 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4726. Min Act: -0.1700
Data Index: 8162894 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4564. Min Act: -0.1700
Data Index: 3986453 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4401. Min Act: -0.1700
Data Index: 1929124 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4564. Min Act: -0.1700
Data Index: 3985086 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4401. Min Act: -0.1700
Data Index: 3378577 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4238. Min Act: -0.1700
Data Index: 8545880 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4238. Min Act: -0.1700
Data Index: 7829539 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4238. Min Act: -0.1700
Data Index: 5453899 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4075. Min Act: -0.1700
Data Index: 2221399 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4238. Min Act: -0.1700
Data Index: 7308443 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4075. Min Act: -0.1700
Data Index: 6040074 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6180. Min Range: -2.6180
Max Act: 2.4075. Min Act: -0.1700
Data Index: 2508092 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19