Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.9748. Min Act: -0.1700
Data Index: 2332399 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.8810. Min Act: -0.1700
Data Index: 3505204 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.8498. Min Act: -0.1700
Data Index: 1035470 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.8498. Min Act: -0.1700
Data Index: 6603132 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.6935. Min Act: -0.1700
Data Index: 8178492 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.6310. Min Act: -0.1700
Data Index: 2766588 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.5373. Min Act: -0.1700
Data Index: 1692810 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.5373. Min Act: -0.1700
Data Index: 4756354 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.5373. Min Act: -0.1700
Data Index: 690311 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.5685. Min Act: -0.1700
Data Index: 1983329 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.5373. Min Act: -0.1700
Data Index: 6020630 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.5060. Min Act: -0.1700
Data Index: 4109881 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.5060. Min Act: -0.1700
Data Index: 1343592 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.4435. Min Act: -0.1700
Data Index: 249927 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.4748. Min Act: -0.1700
Data Index: 3839798 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.4435. Min Act: -0.1700
Data Index: 883466 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.4748. Min Act: -0.1700
Data Index: 6616188 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.5060. Min Act: -0.1700
Data Index: 4969038 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.4123. Min Act: -0.1700
Data Index: 971170 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9748. Min Range: -5.9748
Max Act: 5.4435. Min Act: -0.1700
Data Index: 828453 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19