Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2514 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.7670. Min Act: -0.1700
Data Index: 2126721 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.7357. Min Act: -0.1700
Data Index: 8818039 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6888. Min Act: -0.1700
Data Index: 1848729 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6888. Min Act: -0.1700
Data Index: 3796684 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6732. Min Act: -0.1700
Data Index: 7010587 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6732. Min Act: -0.1700
Data Index: 2458397 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6575. Min Act: -0.1700
Data Index: 6084166 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6575. Min Act: -0.1700
Data Index: 8571454 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6575. Min Act: -0.1700
Data Index: 3601797 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6419. Min Act: -0.1700
Data Index: 3817871 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6419. Min Act: -0.1700
Data Index: 1288099 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6262. Min Act: -0.1700
Data Index: 7521604 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6262. Min Act: -0.1700
Data Index: 3894533 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6262. Min Act: -0.1700
Data Index: 4682509 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.5949. Min Act: -0.1700
Data Index: 6196259 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6106. Min Act: -0.1700
Data Index: 1941402 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6106. Min Act: -0.1700
Data Index: 6196258 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6106. Min Act: -0.1700
Data Index: 2022046 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6106. Min Act: -0.1700
Data Index: 2977775 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7670. Min Range: -3.7670
Max Act: 3.6106. Min Act: -0.1700
Data Index: 7356631 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19