Model: None
Dataset: The Pile
Neuron 997 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.6898. Min Act: -0.1700
Data Index: 9094719 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.5774. Min Act: -0.1700
Data Index: 9792388 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.5613. Min Act: -0.1700
Data Index: 8094157 (The Pile)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.5451. Min Act: -0.1700
Data Index: 9595758 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.5451. Min Act: -0.1700
Data Index: 550426 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.5290. Min Act: -0.1700
Data Index: 9269043 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.5290. Min Act: -0.1700
Data Index: 8350556 (The Pile)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.5128. Min Act: -0.1700
Data Index: 3032320 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4966. Min Act: -0.1700
Data Index: 269880 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4966. Min Act: -0.1700
Data Index: 54506 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4966. Min Act: -0.1700
Data Index: 8086515 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4966. Min Act: -0.1700
Data Index: 8271604 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4804. Min Act: -0.1700
Data Index: 279849 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4804. Min Act: -0.1700
Data Index: 8534951 (The Pile)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4804. Min Act: -0.1700
Data Index: 5845431 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4804. Min Act: -0.1700
Data Index: 9440466 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4804. Min Act: -0.1700
Data Index: 654202 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4804. Min Act: -0.1700
Data Index: 3144824 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4804. Min Act: -0.1700
Data Index: 4788249 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6898. Min Range: -2.6898
Max Act: 2.4642. Min Act: -0.1700
Data Index: 3197653 (The Pile)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19