Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 842 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8407. Min Range: -9.8407
Max Act: 9.8407. Min Act: -0.1700
Data Index: 3448750 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8407. Min Range: -9.8407
Max Act: 9.7157. Min Act: -0.1700
Data Index: 3667632 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8407. Min Range: -9.8407
Max Act: 9.4032. Min Act: -0.1700
Data Index: 3568659 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8407. Min Range: -9.8407
Max Act: 9.4657. Min Act: -0.1700
Data Index: 2412797 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8407. Min Range: -9.8407
Max Act: 9.2782. Min Act: -0.1700
Data Index: 7410266 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8407. Min Range: -9.8407
Max Act: 9.1532. Min Act: -0.1700
Data Index: 5224527 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8407. Min Range: -9.8407
Max Act: 9.0907. Min Act: -0.1700
Data Index: 5851625 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8407. Min Range: -9.8407
Max Act: 9.0282. Min Act: -0.1700
Data Index: 8776548 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8407. Min Range: -9.8407
Max Act: 9.0282. Min Act: -0.1700
Data Index: 4579016 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8407. Min Range: -9.8407
Max Act: 9.0282. Min Act: -0.1700
Data Index: 5511017 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8407. Min Range: -9.8407
Max Act: 8.9657. Min Act: -0.1700
Data Index: 8383779 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8407. Min Range: -9.8407
Max Act: 8.9657. Min Act: -0.1700
Data Index: 5807795 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8407. Min Range: -9.8407
Max Act: 8.9032. Min Act: -0.1700
Data Index: 2568635 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8407. Min Range: -9.8407
Max Act: 8.9032. Min Act: -0.1700
Data Index: 7881480 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8407. Min Range: -9.8407
Max Act: 8.8407. Min Act: -0.1700
Data Index: 7925816 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8407. Min Range: -9.8407
Max Act: 8.8407. Min Act: -0.1700
Data Index: 5790572 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8407. Min Range: -9.8407
Max Act: 8.8407. Min Act: -0.1700
Data Index: 7305648 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8407. Min Range: -9.8407
Max Act: 8.7782. Min Act: -0.1700
Data Index: 6594666 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8407. Min Range: -9.8407
Max Act: 8.7157. Min Act: -0.1700
Data Index: 4455713 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8407. Min Range: -9.8407
Max Act: 8.7157. Min Act: -0.1700
Data Index: 5969065 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19