Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1581 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.6665. Min Act: -0.1700
Data Index: 1386120 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.5415. Min Act: -0.1700
Data Index: 2611664 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.5415. Min Act: -0.1700
Data Index: 8628791 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.4790. Min Act: -0.1700
Data Index: 4677753 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.4790. Min Act: -0.1700
Data Index: 5843592 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.5415. Min Act: -0.1700
Data Index: 953678 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.5103. Min Act: -0.1700
Data Index: 1328996 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.4478. Min Act: -0.1700
Data Index: 8111759 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.4478. Min Act: -0.1700
Data Index: 8209673 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.4478. Min Act: -0.1700
Data Index: 7574243 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.4165. Min Act: -0.1700
Data Index: 7591965 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.3853. Min Act: -0.1700
Data Index: 3259870 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.3853. Min Act: -0.1700
Data Index: 1596716 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.3853. Min Act: -0.1700
Data Index: 8557549 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.3540. Min Act: -0.1700
Data Index: 4422542 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.3228. Min Act: -0.1700
Data Index: 1990906 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.3228. Min Act: -0.1700
Data Index: 5080766 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.2915. Min Act: -0.1700
Data Index: 4180386 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.2915. Min Act: -0.1700
Data Index: 7608226 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.2915. Min Act: -0.1700
Data Index: 7331256 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19