Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1186. Min Range: -6.1186
Max Act: 6.1186. Min Act: -0.1700
Data Index: 726294 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1186. Min Range: -6.1186
Max Act: 6.0248. Min Act: -0.1700
Data Index: 8691427 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1186. Min Range: -6.1186
Max Act: 6.0561. Min Act: -0.1700
Data Index: 3309708 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.9623. Min Act: -0.1700
Data Index: 6507593 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.9311. Min Act: -0.1700
Data Index: 1432747 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.8998. Min Act: -0.1700
Data Index: 5493509 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.8998. Min Act: -0.1700
Data Index: 921024 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.8686. Min Act: -0.1700
Data Index: 3700714 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.8686. Min Act: -0.1700
Data Index: 5742202 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.8686. Min Act: -0.1700
Data Index: 8225767 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.8686. Min Act: -0.1700
Data Index: 6425028 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.8373. Min Act: -0.1700
Data Index: 1394360 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.8373. Min Act: -0.1700
Data Index: 2398875 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.8373. Min Act: -0.1700
Data Index: 2570857 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.8061. Min Act: -0.1700
Data Index: 1809272 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.8061. Min Act: -0.1700
Data Index: 4967367 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.7748. Min Act: -0.1700
Data Index: 414929 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.7748. Min Act: -0.1700
Data Index: 3950200 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.7748. Min Act: -0.1700
Data Index: 1872294 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1186. Min Range: -6.1186
Max Act: 5.7748. Min Act: -0.1700
Data Index: 2097016 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19