Model: None
Dataset: The Pile
Neuron 445 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.1978. Min Act: -0.1700
Data Index: 5357178 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.6353. Min Act: -0.1700
Data Index: 1407851 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.6041. Min Act: -0.1700
Data Index: 3229646 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.4478. Min Act: -0.1700
Data Index: 3029541 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.4791. Min Act: -0.1700
Data Index: 10462433 (The Pile)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.4791. Min Act: -0.1700
Data Index: 6212437 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.4478. Min Act: -0.1700
Data Index: 4746757 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.3541. Min Act: -0.1700
Data Index: 10423722 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.0728. Min Act: -0.1700
Data Index: 10392354 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.5103. Min Act: -0.1700
Data Index: 3868579 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.3853. Min Act: -0.1700
Data Index: 5086605 (The Pile)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.2916. Min Act: -0.1700
Data Index: 6575539 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.1978. Min Act: -0.1700
Data Index: 7382175 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.2916. Min Act: -0.1700
Data Index: 2472675 (The Pile)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.1666. Min Act: -0.1700
Data Index: 8912007 (The Pile)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.1666. Min Act: -0.1700
Data Index: 755304 (The Pile)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.2916. Min Act: -0.1700
Data Index: 6912850 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.0103. Min Act: -0.1700
Data Index: 8693445 (The Pile)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.2603. Min Act: -0.1700
Data Index: 5330763 (The Pile)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6353. Min Range: -8.6353
Max Act: 8.4166. Min Act: -0.1700
Data Index: 1780292 (The Pile)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19