Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2005 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7915. Min Range: -12.7915
Max Act: 12.7915. Min Act: -0.1700
Data Index: 7439899 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7915. Min Range: -12.7915
Max Act: 12.2290. Min Act: -0.1700
Data Index: 3280534 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7915. Min Range: -12.7915
Max Act: 12.1040. Min Act: -0.1700
Data Index: 8297889 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7915. Min Range: -12.7915
Max Act: 12.0415. Min Act: -0.1700
Data Index: 2766277 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.9165. Min Act: -0.1700
Data Index: 102175 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.7915. Min Act: -0.1700
Data Index: 367516 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.7290. Min Act: -0.1700
Data Index: 3171913 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.6665. Min Act: -0.1700
Data Index: 7962026 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.7290. Min Act: -0.1700
Data Index: 7929867 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.6040. Min Act: -0.1700
Data Index: 2917596 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.6040. Min Act: -0.1700
Data Index: 2673997 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.5415. Min Act: -0.1700
Data Index: 5412744 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.5415. Min Act: -0.1700
Data Index: 3111209 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.5415. Min Act: -0.1700
Data Index: 3551779 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.4790. Min Act: -0.1700
Data Index: 4825544 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.4790. Min Act: -0.1700
Data Index: 7244252 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.4165. Min Act: -0.1700
Data Index: 1965337 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.4165. Min Act: -0.1700
Data Index: 2793052 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.4165. Min Act: -0.1700
Data Index: 2229507 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7915. Min Range: -12.7915
Max Act: 11.4165. Min Act: -0.1700
Data Index: 169602 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19