Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5210 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4423. Min Range: -8.4423
Max Act: 8.4423. Min Act: -0.1700
Data Index: 5759535 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.7548. Min Act: -0.1700
Data Index: 7331243 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.6610. Min Act: -0.1700
Data Index: 5486648 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.6298. Min Act: -0.1700
Data Index: 6076277 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.5985. Min Act: -0.1697
Data Index: 4809219 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.5673. Min Act: -0.1700
Data Index: 1711062 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.5048. Min Act: -0.1700
Data Index: 6927466 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.4735. Min Act: -0.1700
Data Index: 5786775 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.4423. Min Act: -0.1700
Data Index: 8462282 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.4110. Min Act: -0.1700
Data Index: 1300255 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.4110. Min Act: -0.1700
Data Index: 5763453 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.4110. Min Act: -0.1700
Data Index: 7570660 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.3798. Min Act: -0.1700
Data Index: 941170 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.3173. Min Act: -0.1700
Data Index: 2668425 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.2860. Min Act: -0.1700
Data Index: 5286041 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.2548. Min Act: -0.1700
Data Index: 7994571 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.2548. Min Act: -0.1700
Data Index: 7293880 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.2548. Min Act: -0.1700
Data Index: 8497921 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.2235. Min Act: -0.1700
Data Index: 6213823 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4423. Min Range: -8.4423
Max Act: 7.2235. Min Act: -0.1690
Data Index: 184134 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19