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

Dataset: The Pile

Neuron 2566 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: 1.4854. Min Range: -1.4854

Max Act: 1.4854. Min Act: -0.0000

Data Index: 728011 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.4676. Min Act: -0.0000

Data Index: 1494763 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.3359. Min Act: -0.0000

Data Index: 94950 (The Pile)

Max Activating Token Index: 262

Text #3

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1702. Min Act: -0.0000

Data Index: 274173 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.2753. Min Act: -0.0000

Data Index: 1990517 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.3304. Min Act: -0.0000

Data Index: 788468 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.2023. Min Act: -0.0000

Data Index: 961258 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1726424 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1776. Min Act: -0.0000

Data Index: 98521 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1057466 (The Pile)

Max Activating Token Index: 981

Text #10

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.2170. Min Act: -0.0000

Data Index: 675652 (The Pile)

Max Activating Token Index: 486

Text #11

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1116. Min Act: -0.0000

Data Index: 707042 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.3593. Min Act: -0.0000

Data Index: 868096 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0862. Min Act: -0.0000

Data Index: 245546 (The Pile)

Max Activating Token Index: 624

Text #14

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.3447. Min Act: -0.0000

Data Index: 1852902 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.2110. Min Act: -0.0000

Data Index: 1980159 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1879. Min Act: -0.0000

Data Index: 1296493 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1973. Min Act: -0.0000

Data Index: 402947 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1189. Min Act: -0.0000

Data Index: 465703 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1328. Min Act: -0.0000

Data Index: 827921 (The Pile)

Max Activating Token Index: 424