Model: None
Dataset: The Pile
Neuron 517 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.7481. Min Act: -0.1700
Data Index: 3451234 (The Pile)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.7481. Min Act: -0.1700
Data Index: 10380739 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.7322. Min Act: -0.1700
Data Index: 3624385 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.7002. Min Act: -0.1700
Data Index: 3587676 (The Pile)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.7162. Min Act: -0.1700
Data Index: 2414301 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.7002. Min Act: -0.1700
Data Index: 5440639 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.7002. Min Act: -0.1700
Data Index: 4718705 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.6842. Min Act: -0.1700
Data Index: 3247183 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.7162. Min Act: -0.1700
Data Index: 3118291 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.7002. Min Act: -0.1700
Data Index: 4514541 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.7002. Min Act: -0.1700
Data Index: 6029703 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.6521. Min Act: -0.1700
Data Index: 6681164 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.6681. Min Act: -0.1700
Data Index: 6149375 (The Pile)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.6681. Min Act: -0.1700
Data Index: 10360589 (The Pile)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.6842. Min Act: -0.1700
Data Index: 7031208 (The Pile)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.6842. Min Act: -0.1700
Data Index: 6859591 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.6361. Min Act: -0.1700
Data Index: 2758900 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.6842. Min Act: -0.1700
Data Index: 1566495 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.6521. Min Act: -0.1700
Data Index: 5259652 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7481. Min Range: -2.7481
Max Act: 2.6681. Min Act: -0.1700
Data Index: 9613415 (The Pile)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19