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

Dataset: The Pile

Neuron 1566 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2568. Min Act: -0.0000

Data Index: 197687 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1544712 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1673980 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1623661 (The Pile)

Max Activating Token Index: 196

Text #4

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2375. Min Act: -0.0000

Data Index: 680585 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1074016 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2436. Min Act: -0.0000

Data Index: 634037 (The Pile)

Max Activating Token Index: 614

Text #7

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1557765 (The Pile)

Max Activating Token Index: 338

Text #8

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1074976 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2395. Min Act: -0.0000

Data Index: 319960 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2227. Min Act: -0.0000

Data Index: 260411 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1727683 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1037477 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1774697 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2261. Min Act: -0.0000

Data Index: 270003 (The Pile)

Max Activating Token Index: 915

Text #15

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1297603 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1445203 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1083340 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2314. Min Act: -0.0000

Data Index: 354901 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1754560 (The Pile)

Max Activating Token Index: 363