Model: None
Dataset: The Pile
Neuron 2006 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.5023. Min Act: -0.1700
Data Index: 4495903 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.4536. Min Act: -0.1700
Data Index: 7328264 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.4698. Min Act: -0.1700
Data Index: 10309448 (The Pile)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.4211. Min Act: -0.1700
Data Index: 10789044 (The Pile)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.4211. Min Act: -0.1700
Data Index: 9684395 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.4048. Min Act: -0.1700
Data Index: 8917475 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.4048. Min Act: -0.1700
Data Index: 7803441 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.3721. Min Act: -0.1700
Data Index: 1787456 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.4048. Min Act: -0.1700
Data Index: 4709404 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.3721. Min Act: -0.1700
Data Index: 9601749 (The Pile)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.3558. Min Act: -0.1700
Data Index: 7324425 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.3558. Min Act: -0.1700
Data Index: 1823450 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.3394. Min Act: -0.1700
Data Index: 10477181 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.3721. Min Act: -0.1700
Data Index: 6362946 (The Pile)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.4048. Min Act: -0.1700
Data Index: 3178631 (The Pile)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.3721. Min Act: -0.1700
Data Index: 617387 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.3558. Min Act: -0.1700
Data Index: 2892205 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.3721. Min Act: -0.1700
Data Index: 4257239 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.3558. Min Act: -0.1700
Data Index: 4204198 (The Pile)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5023. Min Range: -2.5023
Max Act: 2.3066. Min Act: -0.1700
Data Index: 8774031 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19