Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2933 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2725. Min Range: -6.2725
Max Act: 6.2725. Min Act: -0.1700
Data Index: 4363836 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2725. Min Range: -6.2725
Max Act: 6.2412. Min Act: -0.1700
Data Index: 7539765 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2725. Min Range: -6.2725
Max Act: 6.1475. Min Act: -0.1700
Data Index: 5794280 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2725. Min Range: -6.2725
Max Act: 6.0537. Min Act: -0.1700
Data Index: 8114371 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.9600. Min Act: -0.1700
Data Index: 1855422 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.9912. Min Act: -0.1700
Data Index: 7992288 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.9287. Min Act: -0.1700
Data Index: 2574116 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.9287. Min Act: -0.1700
Data Index: 1210515 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.8975. Min Act: -0.1700
Data Index: 2749861 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.8662. Min Act: -0.1700
Data Index: 6309185 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.8662. Min Act: -0.1700
Data Index: 4114863 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.8662. Min Act: -0.1700
Data Index: 591521 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.8350. Min Act: -0.1700
Data Index: 7412323 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.8037. Min Act: -0.1700
Data Index: 7330988 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.8037. Min Act: -0.1700
Data Index: 4917729 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.7725. Min Act: -0.1700
Data Index: 6578021 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.7412. Min Act: -0.1700
Data Index: 7007713 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.7412. Min Act: -0.1700
Data Index: 3608522 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.7412. Min Act: -0.1700
Data Index: 7551385 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2725. Min Range: -6.2725
Max Act: 5.7412. Min Act: -0.1700
Data Index: 8169971 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19