Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6364 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2301. Min Range: -5.2301
Max Act: 5.2301. Min Act: -0.1700
Data Index: 6650103 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2301. Min Range: -5.2301
Max Act: 5.1676. Min Act: -0.1700
Data Index: 721702 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2301. Min Range: -5.2301
Max Act: 5.1364. Min Act: -0.1700
Data Index: 4230318 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2301. Min Range: -5.2301
Max Act: 5.1051. Min Act: -0.1700
Data Index: 5934561 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2301. Min Range: -5.2301
Max Act: 5.0426. Min Act: -0.1700
Data Index: 5295780 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2301. Min Range: -5.2301
Max Act: 5.0739. Min Act: -0.1700
Data Index: 349990 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.9801. Min Act: -0.1700
Data Index: 6779869 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.9489. Min Act: -0.1700
Data Index: 2124673 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.9176. Min Act: -0.1700
Data Index: 5236499 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.9176. Min Act: -0.1700
Data Index: 6925186 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.8551. Min Act: -0.1700
Data Index: 5327708 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.8551. Min Act: -0.1700
Data Index: 4924904 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.8239. Min Act: -0.1700
Data Index: 8118812 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.8239. Min Act: -0.1700
Data Index: 8644935 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.8551. Min Act: -0.1700
Data Index: 12984 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.8239. Min Act: -0.1700
Data Index: 7237124 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.7614. Min Act: -0.1700
Data Index: 1006973 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.7926. Min Act: -0.1700
Data Index: 1096313 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.7614. Min Act: -0.1700
Data Index: 5163518 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2301. Min Range: -5.2301
Max Act: 4.7614. Min Act: -0.1700
Data Index: 1754256 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19