Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.3766. Min Act: -0.1700
Data Index: 4041207 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.4079. Min Act: -0.1700
Data Index: 3328576 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.3454. Min Act: -0.1700
Data Index: 8107536 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.2829. Min Act: -0.1700
Data Index: 2627330 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.2204. Min Act: -0.1700
Data Index: 383852 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.1266. Min Act: -0.1700
Data Index: 7475401 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.0954. Min Act: -0.1700
Data Index: 7531894 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.0329. Min Act: -0.1700
Data Index: 2101054 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.0016. Min Act: -0.1700
Data Index: 583092 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.0016. Min Act: -0.1700
Data Index: 3567335 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.0329. Min Act: -0.1700
Data Index: 4248853 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.0016. Min Act: -0.1700
Data Index: 4848904 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4079. Min Range: -5.4079
Max Act: 4.9704. Min Act: -0.1700
Data Index: 2024133 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4079. Min Range: -5.4079
Max Act: 5.0016. Min Act: -0.1700
Data Index: 7266677 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4079. Min Range: -5.4079
Max Act: 4.9391. Min Act: -0.1700
Data Index: 4479907 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4079. Min Range: -5.4079
Max Act: 4.9391. Min Act: -0.1700
Data Index: 1985246 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4079. Min Range: -5.4079
Max Act: 4.9391. Min Act: -0.1700
Data Index: 6479023 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4079. Min Range: -5.4079
Max Act: 4.9391. Min Act: -0.1700
Data Index: 6822014 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4079. Min Range: -5.4079
Max Act: 4.9391. Min Act: -0.1700
Data Index: 3896376 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4079. Min Range: -5.4079
Max Act: 4.9079. Min Act: -0.1700
Data Index: 4232792 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19