Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 189 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2631. Min Range: -5.2631
Max Act: 5.2631. Min Act: -0.1700
Data Index: 827292 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2631. Min Range: -5.2631
Max Act: 5.2631. Min Act: -0.1700
Data Index: 5768786 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2631. Min Range: -5.2631
Max Act: 5.2319. Min Act: -0.1700
Data Index: 5248684 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2631. Min Range: -5.2631
Max Act: 5.2006. Min Act: -0.1700
Data Index: 1984226 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2631. Min Range: -5.2631
Max Act: 5.1694. Min Act: -0.1700
Data Index: 4227820 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2631. Min Range: -5.2631
Max Act: 5.1069. Min Act: -0.1700
Data Index: 3226744 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2631. Min Range: -5.2631
Max Act: 5.1381. Min Act: -0.1700
Data Index: 3858825 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2631. Min Range: -5.2631
Max Act: 5.0756. Min Act: -0.1700
Data Index: 3250395 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2631. Min Range: -5.2631
Max Act: 5.0756. Min Act: -0.1700
Data Index: 7316564 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2631. Min Range: -5.2631
Max Act: 5.0444. Min Act: -0.1700
Data Index: 2446466 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2631. Min Range: -5.2631
Max Act: 5.0444. Min Act: -0.1700
Data Index: 5628407 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2631. Min Range: -5.2631
Max Act: 4.9819. Min Act: -0.1700
Data Index: 3459497 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2631. Min Range: -5.2631
Max Act: 4.9819. Min Act: -0.1700
Data Index: 5271184 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2631. Min Range: -5.2631
Max Act: 4.9819. Min Act: -0.1700
Data Index: 8666049 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2631. Min Range: -5.2631
Max Act: 4.9506. Min Act: -0.1700
Data Index: 6446394 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2631. Min Range: -5.2631
Max Act: 4.9506. Min Act: -0.1700
Data Index: 2918514 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2631. Min Range: -5.2631
Max Act: 4.9194. Min Act: -0.1700
Data Index: 758344 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2631. Min Range: -5.2631
Max Act: 4.9194. Min Act: -0.1700
Data Index: 7515515 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2631. Min Range: -5.2631
Max Act: 4.9194. Min Act: -0.1700
Data Index: 3533440 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2631. Min Range: -5.2631
Max Act: 4.9194. Min Act: -0.1700
Data Index: 4107915 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19