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

Dataset: The Pile

Neuron 4164 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: 1.6040. Min Range: -1.6040

Max Act: 1.6040. Min Act: -0.0000

Data Index: 720918 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.3621. Min Act: -0.0000

Data Index: 275701 (The Pile)

Max Activating Token Index: 618

Text #2

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.2235. Min Act: -0.0001

Data Index: 1384975 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.0245. Min Act: -0.0000

Data Index: 31857 (The Pile)

Max Activating Token Index: 70

Text #4

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1490134 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9843. Min Act: -0.0000

Data Index: 575798 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1471818 (The Pile)

Max Activating Token Index: 741

Text #7

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9440. Min Act: -0.0000

Data Index: 286440 (The Pile)

Max Activating Token Index: 282

Text #8

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9346. Min Act: -0.0000

Data Index: 804641 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1736145 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1275947 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1389542 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9479. Min Act: -0.0000

Data Index: 1078936 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9732. Min Act: -0.0000

Data Index: 44595 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1257184 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9416. Min Act: -0.0000

Data Index: 613137 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9497. Min Act: -0.0000

Data Index: 275716 (The Pile)

Max Activating Token Index: 412

Text #17

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1723905 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1151277 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9098. Min Act: -0.0000

Data Index: 564586 (The Pile)

Max Activating Token Index: 146