Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 323 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.4711. Min Act: -0.1700
Data Index: 7508223 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.2836. Min Act: -0.1700
Data Index: 1219868 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.2211. Min Act: -0.1700
Data Index: 6013369 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.1898. Min Act: -0.1700
Data Index: 1583871 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.0336. Min Act: -0.1700
Data Index: 8724516 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.0023. Min Act: -0.1700
Data Index: 669238 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.0023. Min Act: -0.1700
Data Index: 4669620 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.0023. Min Act: -0.1700
Data Index: 4431580 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.9711. Min Act: -0.1700
Data Index: 6424394 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.9398. Min Act: -0.1700
Data Index: 6449405 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.8773. Min Act: -0.1700
Data Index: 5280549 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.8773. Min Act: -0.1700
Data Index: 3725713 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.8461. Min Act: -0.1700
Data Index: 919045 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.7836. Min Act: -0.1700
Data Index: 4789748 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.7836. Min Act: -0.1700
Data Index: 1583872 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.8148. Min Act: -0.1700
Data Index: 3866510 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.7836. Min Act: -0.1700
Data Index: 4854244 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.7523. Min Act: -0.1700
Data Index: 8461962 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.7211. Min Act: -0.1700
Data Index: 8726437 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.7211. Min Act: -0.1700
Data Index: 2106516 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19