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

Dataset: The Pile

Neuron 1122 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: 1.0801. Min Range: -1.0801

Max Act: 1.0801. Min Act: 0.0000

Data Index: 959611 (The Pile)

Max Activating Token Index: 691

Text #1

Max Range: 1.0801. Min Range: -1.0801

Max Act: 1.0353. Min Act: -0.0000

Data Index: 1063118 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 1.0801. Min Range: -1.0801

Max Act: 1.0099. Min Act: 0.0000

Data Index: 1549256 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1620880 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9625. Min Act: -0.0000

Data Index: 896725 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 1.0801. Min Range: -1.0801

Max Act: 1.0082. Min Act: -0.0000

Data Index: 1284836 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9465. Min Act: -0.0000

Data Index: 619339 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9450. Min Act: -0.0000

Data Index: 846113 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 1.0801. Min Range: -1.0801

Max Act: 1.0556. Min Act: -0.0000

Data Index: 848132 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8609. Min Act: -0.0000

Data Index: 812795 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8424. Min Act: -0.0000

Data Index: 360960 (The Pile)

Max Activating Token Index: 812

Text #11

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9418. Min Act: 0.0000

Data Index: 1041209 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8849. Min Act: -0.0000

Data Index: 938885 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1929397 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8572. Min Act: -0.0000

Data Index: 639088 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8546. Min Act: 0.0000

Data Index: 959151 (The Pile)

Max Activating Token Index: 844

Text #16

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8784. Min Act: -0.0000

Data Index: 469955 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8283. Min Act: -0.0000

Data Index: 351427 (The Pile)

Max Activating Token Index: 817

Text #18

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1921192 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1341952 (The Pile)

Max Activating Token Index: 1021