Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1000 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2208. Min Range: -9.2208
Max Act: 9.2208. Min Act: -0.1700
Data Index: 7355778 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2208. Min Range: -9.2208
Max Act: 9.0958. Min Act: -0.1700
Data Index: 5836520 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2208. Min Range: -9.2208
Max Act: 9.0333. Min Act: -0.1700
Data Index: 395854 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.9083. Min Act: -0.1700
Data Index: 3507758 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.9708. Min Act: -0.1700
Data Index: 2405453 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.9708. Min Act: -0.1700
Data Index: 6015581 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.9083. Min Act: -0.1700
Data Index: 6127556 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.9708. Min Act: -0.1700
Data Index: 7678814 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.9083. Min Act: -0.1700
Data Index: 4013656 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.8458. Min Act: -0.1700
Data Index: 5836519 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.9083. Min Act: -0.1700
Data Index: 475373 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.9083. Min Act: -0.1700
Data Index: 3613808 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.8458. Min Act: -0.1700
Data Index: 2245134 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.8458. Min Act: -0.1700
Data Index: 7298000 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.8458. Min Act: -0.1700
Data Index: 6182520 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.8458. Min Act: -0.1700
Data Index: 4419116 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.7833. Min Act: -0.1700
Data Index: 5502273 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.7833. Min Act: -0.1700
Data Index: 296738 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.7833. Min Act: -0.1700
Data Index: 1673418 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2208. Min Range: -9.2208
Max Act: 8.7208. Min Act: -0.1700
Data Index: 1338456 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19