Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1437 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0015. Min Range: -5.0015
Max Act: 5.0015. Min Act: -0.1700
Data Index: 4168811 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.9703. Min Act: -0.1700
Data Index: 4663485 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.9390. Min Act: -0.1700
Data Index: 2383664 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.9703. Min Act: -0.1700
Data Index: 5026863 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.8453. Min Act: -0.1700
Data Index: 5990067 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.8453. Min Act: -0.1700
Data Index: 8062626 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.8140. Min Act: -0.1700
Data Index: 724298 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.8140. Min Act: -0.1700
Data Index: 4485775 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7828. Min Act: -0.1700
Data Index: 4990802 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7828. Min Act: -0.1700
Data Index: 4187426 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7828. Min Act: -0.1700
Data Index: 2466774 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7515. Min Act: -0.1700
Data Index: 2482282 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7515. Min Act: -0.1700
Data Index: 3816207 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7515. Min Act: -0.1700
Data Index: 7534525 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7515. Min Act: -0.1700
Data Index: 5802007 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7515. Min Act: -0.1700
Data Index: 1794812 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7515. Min Act: -0.1700
Data Index: 4833578 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7203. Min Act: -0.1700
Data Index: 5030328 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7203. Min Act: -0.1700
Data Index: 5769168 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0015. Min Range: -5.0015
Max Act: 4.7203. Min Act: -0.1700
Data Index: 2694898 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19