Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4232 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.9188. Min Act: -0.1700
Data Index: 883006 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.8235. Min Act: -0.1700
Data Index: 6523751 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.8235. Min Act: -0.1700
Data Index: 8260972 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.8076. Min Act: -0.1700
Data Index: 2183766 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7917. Min Act: -0.1700
Data Index: 7047211 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7917. Min Act: -0.1700
Data Index: 1209410 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7757. Min Act: -0.1700
Data Index: 6624566 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7757. Min Act: -0.1700
Data Index: 4171028 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7917. Min Act: -0.1700
Data Index: 4411083 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7598. Min Act: -0.1700
Data Index: 173032 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7598. Min Act: -0.1700
Data Index: 1642475 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7598. Min Act: -0.1700
Data Index: 3744096 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7279. Min Act: -0.1700
Data Index: 5464797 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7438. Min Act: -0.1700
Data Index: 3586193 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7119. Min Act: -0.1700
Data Index: 6910182 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7279. Min Act: -0.1700
Data Index: 8432119 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7438. Min Act: -0.1700
Data Index: 7685756 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7279. Min Act: -0.1700
Data Index: 426729 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.7119. Min Act: -0.1700
Data Index: 4026572 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9188. Min Range: -2.9188
Max Act: 2.6959. Min Act: -0.1700
Data Index: 3537440 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19