Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1741. Min Range: -6.1741
Max Act: 6.1741. Min Act: -0.1700
Data Index: 2957658 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1741. Min Range: -6.1741
Max Act: 6.0803. Min Act: -0.1700
Data Index: 3702355 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1741. Min Range: -6.1741
Max Act: 6.0491. Min Act: -0.1700
Data Index: 774928 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9866. Min Act: -0.1695
Data Index: 4383548 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9866. Min Act: -0.1700
Data Index: 7169703 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9553. Min Act: -0.1700
Data Index: 7397926 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9553. Min Act: -0.1700
Data Index: 2499242 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9553. Min Act: -0.1700
Data Index: 1749520 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9241. Min Act: -0.1700
Data Index: 3138956 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9241. Min Act: -0.1700
Data Index: 7651969 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9241. Min Act: -0.1700
Data Index: 1829778 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9241. Min Act: -0.1700
Data Index: 7169705 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9241. Min Act: -0.1700
Data Index: 8018477 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9553. Min Act: -0.1700
Data Index: 8018478 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.9241. Min Act: -0.1699
Data Index: 1708915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.8928. Min Act: -0.1700
Data Index: 7087512 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.8928. Min Act: -0.1700
Data Index: 4088550 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.8928. Min Act: -0.1700
Data Index: 6866178 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.8928. Min Act: -0.1700
Data Index: 6092876 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1741. Min Range: -6.1741
Max Act: 5.8928. Min Act: -0.1700
Data Index: 5285729 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19