Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 289 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1541. Min Act: -0.0000

Data Index: 959604 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1258. Min Act: -0.0000

Data Index: 603606 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1915397 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1899991 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1227405 (The Pile)

Max Activating Token Index: 527

Text #5

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1500434 (The Pile)

Max Activating Token Index: 306

Text #6

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1076901 (The Pile)

Max Activating Token Index: 69

Text #7

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1592788 (The Pile)

Max Activating Token Index: 694

Text #8

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1573157 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1261640 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1090. Min Act: -0.0000

Data Index: 725275 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1065. Min Act: -0.0000

Data Index: 841711 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1043. Min Act: -0.0000

Data Index: 99954 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1095. Min Act: -0.0000

Data Index: 32524 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1598046 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1149. Min Act: -0.0000

Data Index: 759553 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.0985. Min Act: -0.0000

Data Index: 138876 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1910882 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.0943. Min Act: -0.0000

Data Index: 708594 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1226972 (The Pile)

Max Activating Token Index: 775