Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2045 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.7024. Min Act: -0.1700
Data Index: 2602040 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.5774. Min Act: -0.1700
Data Index: 1229833 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.3899. Min Act: -0.1700
Data Index: 4389882 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.3899. Min Act: -0.1700
Data Index: 4885155 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.3274. Min Act: -0.1700
Data Index: 4990902 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.3274. Min Act: -0.1700
Data Index: 5636438 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.2024. Min Act: -0.1700
Data Index: 611236 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.2649. Min Act: -0.1700
Data Index: 4965414 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.2649. Min Act: -0.1700
Data Index: 1849172 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.2649. Min Act: -0.1700
Data Index: 6618715 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.3274. Min Act: -0.1700
Data Index: 4081045 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.2024. Min Act: -0.1700
Data Index: 865915 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.2649. Min Act: -0.1700
Data Index: 8250141 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.2024. Min Act: -0.1700
Data Index: 6774892 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.1399. Min Act: -0.1700
Data Index: 6848518 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.1399. Min Act: -0.1700
Data Index: 4126190 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.1399. Min Act: -0.1700
Data Index: 8649750 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.2024. Min Act: -0.1700
Data Index: 5490507 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.0774. Min Act: -0.1700
Data Index: 1953982 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7024. Min Range: -8.7024
Max Act: 8.0774. Min Act: -0.1700
Data Index: 7952213 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19