Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2461 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5731. Min Range: -8.5731
Max Act: 8.5731. Min Act: -0.1700
Data Index: 2472153 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5731. Min Range: -8.5731
Max Act: 8.5106. Min Act: -0.1700
Data Index: 6451246 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5731. Min Range: -8.5731
Max Act: 8.3856. Min Act: -0.1700
Data Index: 8011985 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5731. Min Range: -8.5731
Max Act: 8.3856. Min Act: -0.1700
Data Index: 4570099 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5731. Min Range: -8.5731
Max Act: 8.2606. Min Act: -0.1700
Data Index: 7030927 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5731. Min Range: -8.5731
Max Act: 8.1981. Min Act: -0.1700
Data Index: 796993 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5731. Min Range: -8.5731
Max Act: 8.1981. Min Act: -0.1700
Data Index: 2998209 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5731. Min Range: -8.5731
Max Act: 8.1356. Min Act: -0.1700
Data Index: 5908774 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5731. Min Range: -8.5731
Max Act: 8.1356. Min Act: -0.1700
Data Index: 1181180 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5731. Min Range: -8.5731
Max Act: 8.0106. Min Act: -0.1700
Data Index: 7598977 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5731. Min Range: -8.5731
Max Act: 8.0106. Min Act: -0.1700
Data Index: 5453215 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5731. Min Range: -8.5731
Max Act: 7.9481. Min Act: -0.1700
Data Index: 1760827 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5731. Min Range: -8.5731
Max Act: 7.9481. Min Act: -0.1700
Data Index: 4857499 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5731. Min Range: -8.5731
Max Act: 7.8856. Min Act: -0.1700
Data Index: 6053844 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5731. Min Range: -8.5731
Max Act: 7.8856. Min Act: -0.1700
Data Index: 5154249 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5731. Min Range: -8.5731
Max Act: 7.8856. Min Act: -0.1700
Data Index: 880963 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5731. Min Range: -8.5731
Max Act: 7.9481. Min Act: -0.1700
Data Index: 1968898 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5731. Min Range: -8.5731
Max Act: 7.8231. Min Act: -0.1700
Data Index: 326782 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5731. Min Range: -8.5731
Max Act: 7.8231. Min Act: -0.1700
Data Index: 3323368 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5731. Min Range: -8.5731
Max Act: 7.7606. Min Act: -0.1700
Data Index: 6952625 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19