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

Dataset: The Pile

Neuron 3865 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.4170. Min Act: -0.0000

Data Index: 1518988 (The Pile)

Max Activating Token Index: 391

Text #1

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.1419. Min Act: -0.0000

Data Index: 1866199 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.0633. Min Act: -0.0000

Data Index: 471130 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.0340. Min Act: -0.0000

Data Index: 11226 (The Pile)

Max Activating Token Index: 973

Text #4

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.0289. Min Act: -0.0000

Data Index: 47833 (The Pile)

Max Activating Token Index: 546

Text #5

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9599. Min Act: -0.0000

Data Index: 615395 (The Pile)

Max Activating Token Index: 786

Text #6

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.0081. Min Act: -0.0000

Data Index: 1196233 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9538. Min Act: -0.0000

Data Index: 76614 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9550. Min Act: -0.0000

Data Index: 1347466 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9655. Min Act: -0.0000

Data Index: 599205 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.0238. Min Act: -0.0000

Data Index: 1312563 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.8800. Min Act: -0.0000

Data Index: 265314 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9551. Min Act: -0.0000

Data Index: 766603 (The Pile)

Max Activating Token Index: 364

Text #13

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9162. Min Act: -0.0000

Data Index: 316540 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1651689 (The Pile)

Max Activating Token Index: 454

Text #15

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1240829 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9251. Min Act: -0.0000

Data Index: 43283 (The Pile)

Max Activating Token Index: 582

Text #17

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.8954. Min Act: -0.0000

Data Index: 941230 (The Pile)

Max Activating Token Index: 38

Text #18

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1279005 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.8444. Min Act: -0.0000

Data Index: 930057 (The Pile)

Max Activating Token Index: 917