Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4166 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.5608. Min Act: -0.0000

Data Index: 467660 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.5148. Min Act: -0.0000

Data Index: 971131 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.5061. Min Act: -0.0000

Data Index: 522982 (The Pile)

Max Activating Token Index: 623

Text #3

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.3834. Min Act: -0.0000

Data Index: 857608 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.3699. Min Act: -0.0000

Data Index: 1459893 (The Pile)

Max Activating Token Index: 343

Text #5

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.3237. Min Act: -0.0000

Data Index: 1190873 (The Pile)

Max Activating Token Index: 866

Text #6

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.3487. Min Act: -0.0000

Data Index: 1263459 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.2106. Min Act: -0.0000

Data Index: 1466614 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1029713 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1881. Min Act: -0.0000

Data Index: 257460 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1603365 (The Pile)

Max Activating Token Index: 209

Text #11

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1382937 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1903675 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1278. Min Act: -0.0000

Data Index: 947141 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1570. Min Act: -0.0000

Data Index: 132111 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1553. Min Act: -0.0000

Data Index: 1794828 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1351. Min Act: -0.0000

Data Index: 1124547 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1381. Min Act: -0.0000

Data Index: 584462 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1324. Min Act: -0.0000

Data Index: 1112829 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1307. Min Act: -0.0000

Data Index: 562605 (The Pile)

Max Activating Token Index: 194