Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 899 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.4631. Min Act: -0.1700
Data Index: 1570241 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.3693. Min Act: -0.1700
Data Index: 4538339 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.3381. Min Act: -0.1700
Data Index: 1690591 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.1506. Min Act: -0.1700
Data Index: 1774497 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.1193. Min Act: -0.1700
Data Index: 2997075 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.0568. Min Act: -0.1700
Data Index: 3263537 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.0568. Min Act: -0.1700
Data Index: 2292680 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9943. Min Act: -0.1700
Data Index: 6359660 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9631. Min Act: -0.1700
Data Index: 4425481 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9631. Min Act: -0.1700
Data Index: 8021256 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9318. Min Act: -0.1700
Data Index: 8522571 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9006. Min Act: -0.1700
Data Index: 8012335 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9318. Min Act: -0.1700
Data Index: 5866106 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8693. Min Act: -0.1700
Data Index: 3864625 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8693. Min Act: -0.1700
Data Index: 1684780 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9006. Min Act: -0.1700
Data Index: 2525453 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8693. Min Act: -0.1700
Data Index: 5570372 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8693. Min Act: -0.1700
Data Index: 3537655 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8693. Min Act: -0.1700
Data Index: 7901516 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8693. Min Act: -0.1700
Data Index: 6297557 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19