Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4499 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2579. Min Range: -4.2579
Max Act: 4.2579. Min Act: -0.1700
Data Index: 1594747 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2579. Min Range: -4.2579
Max Act: 4.2266. Min Act: -0.1700
Data Index: 210594 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2579. Min Range: -4.2579
Max Act: 4.1641. Min Act: -0.1700
Data Index: 58504 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2579. Min Range: -4.2579
Max Act: 4.0704. Min Act: -0.1700
Data Index: 1036696 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2579. Min Range: -4.2579
Max Act: 4.0391. Min Act: -0.1700
Data Index: 5930099 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2579. Min Range: -4.2579
Max Act: 4.0079. Min Act: -0.1700
Data Index: 577968 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.9766. Min Act: -0.1700
Data Index: 8161697 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.9141. Min Act: -0.1700
Data Index: 8611472 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.8828. Min Act: -0.1700
Data Index: 2487460 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.8515. Min Act: -0.1700
Data Index: 7645627 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.8515. Min Act: -0.1700
Data Index: 8161703 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.8203. Min Act: -0.1700
Data Index: 2070703 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.8203. Min Act: -0.1700
Data Index: 2143424 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.8203. Min Act: -0.1700
Data Index: 2070708 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.8203. Min Act: -0.1700
Data Index: 34821 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.7890. Min Act: -0.1700
Data Index: 4803589 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.7890. Min Act: -0.1700
Data Index: 3651913 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.7890. Min Act: -0.1700
Data Index: 4792549 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.7577. Min Act: -0.1700
Data Index: 503533 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2579. Min Range: -4.2579
Max Act: 3.7577. Min Act: -0.1700
Data Index: 1239666 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19