Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4852. Min Range: -6.4852
Max Act: 6.4852. Min Act: -0.1700
Data Index: 8483109 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4852. Min Range: -6.4852
Max Act: 6.2352. Min Act: -0.1700
Data Index: 1446909 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4852. Min Range: -6.4852
Max Act: 6.1727. Min Act: -0.1700
Data Index: 6455980 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4852. Min Range: -6.4852
Max Act: 6.1414. Min Act: -0.1700
Data Index: 7167267 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4852. Min Range: -6.4852
Max Act: 6.0164. Min Act: -0.1700
Data Index: 8395771 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.9852. Min Act: -0.1700
Data Index: 3730992 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.9539. Min Act: -0.1700
Data Index: 2854312 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.9539. Min Act: -0.1700
Data Index: 5562757 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.9539. Min Act: -0.1700
Data Index: 8746701 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.9539. Min Act: -0.1700
Data Index: 6110306 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.9227. Min Act: -0.1700
Data Index: 3883881 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.9227. Min Act: -0.1700
Data Index: 4316238 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.8914. Min Act: -0.1700
Data Index: 6083261 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.8914. Min Act: -0.1700
Data Index: 2668085 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.8602. Min Act: -0.1700
Data Index: 5226645 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.8602. Min Act: -0.1700
Data Index: 563474 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.8289. Min Act: -0.1700
Data Index: 6543492 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.8602. Min Act: -0.1700
Data Index: 8370734 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.8914. Min Act: -0.1700
Data Index: 5649226 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4852. Min Range: -6.4852
Max Act: 5.8602. Min Act: -0.1700
Data Index: 4901260 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19