Model: None
Dataset: The Pile
Neuron 2235 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.8584. Min Act: -0.1700
Data Index: 643048 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.8584. Min Act: -0.1700
Data Index: 2438501 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.8115. Min Act: -0.1700
Data Index: 4320254 (The Pile)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7802. Min Act: -0.1700
Data Index: 3802097 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7646. Min Act: -0.1700
Data Index: 8854830 (The Pile)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7646. Min Act: -0.1700
Data Index: 4672187 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7333. Min Act: -0.1700
Data Index: 4730626 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7333. Min Act: -0.1700
Data Index: 9317359 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7333. Min Act: -0.1697
Data Index: 3643336 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7176. Min Act: -0.1700
Data Index: 2687136 (The Pile)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7176. Min Act: -0.1699
Data Index: 9352739 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7176. Min Act: -0.1700
Data Index: 7996270 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7020. Min Act: -0.1695
Data Index: 6949629 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7020. Min Act: -0.1700
Data Index: 5399009 (The Pile)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.7020. Min Act: -0.1700
Data Index: 929564 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.6863. Min Act: -0.1700
Data Index: 4740691 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.6863. Min Act: -0.1700
Data Index: 5830350 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.6863. Min Act: -0.1700
Data Index: 3174003 (The Pile)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.6707. Min Act: -0.1700
Data Index: 3283393 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8584. Min Range: -3.8584
Max Act: 3.6707. Min Act: -0.1700
Data Index: 941533 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19