Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2913 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6176. Min Range: -8.6176
Max Act: 8.6176. Min Act: -0.1700
Data Index: 6525912 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6176. Min Range: -8.6176
Max Act: 8.3676. Min Act: -0.1700
Data Index: 5762005 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6176. Min Range: -8.6176
Max Act: 8.1801. Min Act: -0.1700
Data Index: 4839126 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6176. Min Range: -8.6176
Max Act: 8.1801. Min Act: -0.1700
Data Index: 8630344 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6176. Min Range: -8.6176
Max Act: 8.1801. Min Act: -0.1700
Data Index: 7331087 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6176. Min Range: -8.6176
Max Act: 8.1801. Min Act: -0.1700
Data Index: 7599129 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6176. Min Range: -8.6176
Max Act: 8.1176. Min Act: -0.1700
Data Index: 455810 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6176. Min Range: -8.6176
Max Act: 8.1176. Min Act: -0.1700
Data Index: 881611 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6176. Min Range: -8.6176
Max Act: 8.1176. Min Act: -0.1700
Data Index: 8267548 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6176. Min Range: -8.6176
Max Act: 8.0551. Min Act: -0.1700
Data Index: 64466 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6176. Min Range: -8.6176
Max Act: 7.9614. Min Act: -0.1700
Data Index: 8581215 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6176. Min Range: -8.6176
Max Act: 7.9301. Min Act: -0.1700
Data Index: 76323 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6176. Min Range: -8.6176
Max Act: 7.8989. Min Act: -0.1700
Data Index: 3837179 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6176. Min Range: -8.6176
Max Act: 7.8989. Min Act: -0.1700
Data Index: 8175558 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6176. Min Range: -8.6176
Max Act: 7.9301. Min Act: -0.1700
Data Index: 7295116 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6176. Min Range: -8.6176
Max Act: 7.8676. Min Act: -0.1700
Data Index: 64463 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6176. Min Range: -8.6176
Max Act: 7.8676. Min Act: -0.1700
Data Index: 4871214 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6176. Min Range: -8.6176
Max Act: 7.8051. Min Act: -0.1700
Data Index: 8401063 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6176. Min Range: -8.6176
Max Act: 7.8364. Min Act: -0.1700
Data Index: 2946822 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6176. Min Range: -8.6176
Max Act: 7.8364. Min Act: -0.1700
Data Index: 1139812 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19