Model: None
Dataset: The Pile
Neuron 468 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.9477. Min Act: -0.1700
Data Index: 6374263 (The Pile)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.9477. Min Act: -0.1700
Data Index: 4290396 (The Pile)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.9477. Min Act: -0.1700
Data Index: 3829477 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.9477. Min Act: -0.1700
Data Index: 562192 (The Pile)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8842. Min Act: -0.1700
Data Index: 7181786 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.9001. Min Act: -0.1700
Data Index: 6253359 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.9001. Min Act: -0.1700
Data Index: 6227927 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.9001. Min Act: -0.1700
Data Index: 2586250 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8842. Min Act: -0.1699
Data Index: 685258 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8684. Min Act: -0.1700
Data Index: 4808821 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8684. Min Act: -0.1700
Data Index: 7820956 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8842. Min Act: -0.1700
Data Index: 7598120 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8684. Min Act: -0.1700
Data Index: 5193808 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8525. Min Act: -0.1700
Data Index: 2724716 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8525. Min Act: -0.1699
Data Index: 3748197 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8684. Min Act: -0.1700
Data Index: 1814122 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8684. Min Act: -0.1700
Data Index: 6043496 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8525. Min Act: -0.1700
Data Index: 7460929 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8842. Min Act: -0.1700
Data Index: 5245127 (The Pile)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9477. Min Range: -2.9477
Max Act: 2.8525. Min Act: -0.1700
Data Index: 8976681 (The Pile)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19