Model: None
Dataset: The Pile
Neuron 2566 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.7409. Min Act: -0.1700
Data Index: 9623099 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.7096. Min Act: -0.1700
Data Index: 685250 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6940. Min Act: -0.1700
Data Index: 4756889 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6940. Min Act: -0.1700
Data Index: 1914782 (The Pile)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6783. Min Act: -0.1700
Data Index: 2900971 (The Pile)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6783. Min Act: -0.1700
Data Index: 4233947 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6783. Min Act: -0.1700
Data Index: 7491147 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6783. Min Act: -0.1700
Data Index: 2747075 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6470. Min Act: -0.1700
Data Index: 1772154 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6470. Min Act: -0.1700
Data Index: 352775 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6470. Min Act: -0.1700
Data Index: 7488678 (The Pile)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6314. Min Act: -0.1700
Data Index: 6542782 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6314. Min Act: -0.1700
Data Index: 5442965 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6314. Min Act: -0.1700
Data Index: 8579950 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6314. Min Act: -0.1700
Data Index: 4930249 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6157. Min Act: -0.1700
Data Index: 4091798 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6157. Min Act: -0.1700
Data Index: 6607837 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6157. Min Act: -0.1700
Data Index: 7392453 (The Pile)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6157. Min Act: -0.1700
Data Index: 6984848 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7409. Min Range: -3.7409
Max Act: 3.6157. Min Act: -0.1700
Data Index: 8038826 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19