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

Dataset: The Pile

Neuron 1995 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7977. Min Range: -4.7977

Max Act: 4.7977. Min Act: -0.0000

Data Index: 1883851 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 4.7977. Min Range: -4.7977

Max Act: 4.4213. Min Act: -0.0000

Data Index: 903571 (The Pile)

Max Activating Token Index: 870

Text #2

Max Range: 4.7977. Min Range: -4.7977

Max Act: 4.5975. Min Act: -0.0000

Data Index: 1097968 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 4.7977. Min Range: -4.7977

Max Act: 4.3120. Min Act: -0.0000

Data Index: 1726421 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 4.7977. Min Range: -4.7977

Max Act: 4.1748. Min Act: -0.0000

Data Index: 1581065 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.7359. Min Act: -0.0000

Data Index: 714749 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 4.7977. Min Range: -4.7977

Max Act: 4.3256. Min Act: -0.0000

Data Index: 1819607 (The Pile)

Max Activating Token Index: 694

Text #7

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.9281. Min Act: -0.0000

Data Index: 713863 (The Pile)

Max Activating Token Index: 308

Text #8

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.7395. Min Act: -0.0000

Data Index: 752129 (The Pile)

Max Activating Token Index: 748

Text #9

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.9490. Min Act: -0.0000

Data Index: 1016330 (The Pile)

Max Activating Token Index: 364

Text #10

Max Range: 4.7977. Min Range: -4.7977

Max Act: 4.0848. Min Act: -0.0000

Data Index: 1171777 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.7607. Min Act: -0.0000

Data Index: 1969584 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.8721. Min Act: -0.0000

Data Index: 799842 (The Pile)

Max Activating Token Index: 475

Text #13

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.3768. Min Act: -0.0000

Data Index: 1941163 (The Pile)

Max Activating Token Index: 897

Text #14

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.8084. Min Act: -0.0000

Data Index: 470408 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.5244. Min Act: -0.0000

Data Index: 1806261 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.3727. Min Act: -0.0000

Data Index: 812213 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 4.7977. Min Range: -4.7977

Max Act: 2.9715. Min Act: -0.0000

Data Index: 148804 (The Pile)

Max Activating Token Index: 526

Text #18

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.0162. Min Act: -0.0000

Data Index: 1934517 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 4.7977. Min Range: -4.7977

Max Act: 3.0421. Min Act: -0.0000

Data Index: 839638 (The Pile)

Max Activating Token Index: 551