Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4148 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1707. Min Range: -6.1707
Max Act: 6.1707. Min Act: -0.1700
Data Index: 3395362 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1707. Min Range: -6.1707
Max Act: 6.1395. Min Act: -0.1700
Data Index: 1287746 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1707. Min Range: -6.1707
Max Act: 6.0457. Min Act: -0.1700
Data Index: 1776325 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1707. Min Range: -6.1707
Max Act: 6.0145. Min Act: -0.1700
Data Index: 4093137 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.9832. Min Act: -0.1700
Data Index: 6801449 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.9832. Min Act: -0.1700
Data Index: 8048852 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.8895. Min Act: -0.1700
Data Index: 1267739 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.8895. Min Act: -0.1700
Data Index: 3438477 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.7957. Min Act: -0.1700
Data Index: 5133910 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.7957. Min Act: -0.1700
Data Index: 1870327 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.7957. Min Act: -0.1700
Data Index: 544509 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.7957. Min Act: -0.1700
Data Index: 4557099 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.7957. Min Act: -0.1700
Data Index: 2055493 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.7645. Min Act: -0.1700
Data Index: 2745057 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.7645. Min Act: -0.1700
Data Index: 5669746 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.7645. Min Act: -0.1700
Data Index: 2222267 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.7645. Min Act: -0.1700
Data Index: 8751076 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.7645. Min Act: -0.1700
Data Index: 4682262 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.7020. Min Act: -0.1700
Data Index: 4411520 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1707. Min Range: -6.1707
Max Act: 5.6707. Min Act: -0.1700
Data Index: 2745058 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19