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

Dataset: The Pile

Neuron 4507 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.5635. Min Act: -0.0000

Data Index: 277022 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.4769. Min Act: -0.0000

Data Index: 710181 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1221833 (The Pile)

Max Activating Token Index: 941

Text #3

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2224. Min Act: -0.0000

Data Index: 1672634 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3700. Min Act: -0.0000

Data Index: 990973 (The Pile)

Max Activating Token Index: 890

Text #5

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3718. Min Act: -0.0000

Data Index: 92599 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3475. Min Act: -0.0000

Data Index: 560371 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2647. Min Act: -0.0000

Data Index: 693859 (The Pile)

Max Activating Token Index: 565

Text #8

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1197205 (The Pile)

Max Activating Token Index: 731

Text #9

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3211. Min Act: -0.0000

Data Index: 1647921 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2992. Min Act: -0.0000

Data Index: 448960 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3663. Min Act: -0.0000

Data Index: 205535 (The Pile)

Max Activating Token Index: 578

Text #12

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3569. Min Act: -0.0000

Data Index: 216900 (The Pile)

Max Activating Token Index: 877

Text #13

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2378. Min Act: -0.0000

Data Index: 150598 (The Pile)

Max Activating Token Index: 773

Text #14

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1811145 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2362. Min Act: -0.0000

Data Index: 1817912 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2099. Min Act: -0.0000

Data Index: 720683 (The Pile)

Max Activating Token Index: 706

Text #17

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2131. Min Act: -0.0000

Data Index: 64728 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.1757. Min Act: -0.0000

Data Index: 488909 (The Pile)

Max Activating Token Index: 871

Text #19

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.1914. Min Act: -0.0000

Data Index: 921038 (The Pile)

Max Activating Token Index: 328