Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1742 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0588. Min Range: -4.0588
Max Act: 4.0588. Min Act: -0.1700
Data Index: 414000 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0588. Min Range: -4.0588
Max Act: 4.0588. Min Act: -0.1700
Data Index: 2821155 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.9963. Min Act: -0.1700
Data Index: 8591219 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.9651. Min Act: -0.1700
Data Index: 8322919 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.9338. Min Act: -0.1700
Data Index: 8026154 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.9338. Min Act: -0.1700
Data Index: 4712361 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.9025. Min Act: -0.1700
Data Index: 8075617 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.9025. Min Act: -0.1700
Data Index: 4618028 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.9025. Min Act: -0.1700
Data Index: 5260497 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.8400. Min Act: -0.1700
Data Index: 5382129 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.8713. Min Act: -0.1700
Data Index: 1217684 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.9025. Min Act: -0.1700
Data Index: 3363699 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.8713. Min Act: -0.1700
Data Index: 4501796 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.8400. Min Act: -0.1700
Data Index: 1587351 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.8713. Min Act: -0.1700
Data Index: 5579880 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.8713. Min Act: -0.1700
Data Index: 1058283 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.8713. Min Act: -0.1700
Data Index: 836491 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.8400. Min Act: -0.1700
Data Index: 3905645 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.8400. Min Act: -0.1700
Data Index: 3233862 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0588. Min Range: -4.0588
Max Act: 3.8244. Min Act: -0.1700
Data Index: 3619795 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19