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

Dataset: The Pile

Neuron 3072 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: 0.5835. Min Range: -0.5835

Max Act: 0.5835. Min Act: -0.0000

Data Index: 894917 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5645. Min Act: -0.0000

Data Index: 159231 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3403. Min Act: -0.0000

Data Index: 577618 (The Pile)

Max Activating Token Index: 65

Text #3

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3304. Min Act: -0.0000

Data Index: 469905 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1348473 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1657355 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3403. Min Act: -0.0000

Data Index: 183985 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3210. Min Act: -0.0001

Data Index: 1323851 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3080. Min Act: -0.0000

Data Index: 686969 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1552701 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1447330 (The Pile)

Max Activating Token Index: 322

Text #11

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1673823 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.2920. Min Act: -0.0000

Data Index: 999085 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3340. Min Act: -0.0000

Data Index: 46069 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.2791. Min Act: -0.0000

Data Index: 732967 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3222. Min Act: -0.0000

Data Index: 373554 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3000. Min Act: -0.0000

Data Index: 633364 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.2784. Min Act: -0.0000

Data Index: 866074 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1175646 (The Pile)

Max Activating Token Index: 958

Text #19

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.2665. Min Act: -0.0000

Data Index: 876352 (The Pile)

Max Activating Token Index: 669