Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5122 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.7729. Min Act: -0.1700
Data Index: 1952454 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.7104. Min Act: -0.1700
Data Index: 1952456 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.5854. Min Act: -0.1700
Data Index: 8097164 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.5854. Min Act: -0.1700
Data Index: 5819090 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.5541. Min Act: -0.1700
Data Index: 1516838 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.5541. Min Act: -0.1700
Data Index: 450496 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.5229. Min Act: -0.1700
Data Index: 2307731 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.4604. Min Act: -0.1700
Data Index: 1551817 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.4604. Min Act: -0.1700
Data Index: 4473575 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.4604. Min Act: -0.1700
Data Index: 1190807 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.4291. Min Act: -0.1700
Data Index: 2897759 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.4291. Min Act: -0.1700
Data Index: 1738292 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.3979. Min Act: -0.1700
Data Index: 3197768 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.3979. Min Act: -0.1700
Data Index: 6937344 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.3979. Min Act: -0.1700
Data Index: 286183 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.3666. Min Act: -0.1700
Data Index: 8191140 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.3666. Min Act: -0.1700
Data Index: 3586813 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.3666. Min Act: -0.1700
Data Index: 3379259 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.3666. Min Act: -0.1700
Data Index: 2665011 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7729. Min Range: -6.7729
Max Act: 6.3666. Min Act: -0.1700
Data Index: 3403270 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19