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

Dataset: The Pile

Neuron 2581 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: 0.9250. Min Range: -0.9250

Max Act: 0.9250. Min Act: -0.0000

Data Index: 930511 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7699. Min Act: -0.0000

Data Index: 306872 (The Pile)

Max Activating Token Index: 625

Text #2

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1896500 (The Pile)

Max Activating Token Index: 446

Text #3

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6633. Min Act: -0.0000

Data Index: 44441 (The Pile)

Max Activating Token Index: 875

Text #4

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7971. Min Act: -0.0000

Data Index: 748523 (The Pile)

Max Activating Token Index: 840

Text #5

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6655. Min Act: -0.0000

Data Index: 287893 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1066253 (The Pile)

Max Activating Token Index: 788

Text #7

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1501016 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6747. Min Act: -0.0000

Data Index: 762392 (The Pile)

Max Activating Token Index: 664

Text #9

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6516. Min Act: -0.0000

Data Index: 940923 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1267059 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6393. Min Act: -0.0000

Data Index: 223920 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1279137 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1001387 (The Pile)

Max Activating Token Index: 494

Text #14

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1671019 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1866643 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1605431 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6304. Min Act: -0.0000

Data Index: 461748 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6061. Min Act: -0.0000

Data Index: 419790 (The Pile)

Max Activating Token Index: 840

Text #19

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.5833. Min Act: -0.0000

Data Index: 240274 (The Pile)

Max Activating Token Index: 759