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

Dataset: The Pile

Neuron 1850 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: 0.3048. Min Range: -0.3048

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1580964 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2212. Min Act: -0.0000

Data Index: 530019 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2149. Min Act: -0.0000

Data Index: 86602 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2172. Min Act: -0.0000

Data Index: 140914 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1963. Min Act: -0.0000

Data Index: 145754 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1432768 (The Pile)

Max Activating Token Index: 85

Text #6

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1944. Min Act: -0.0000

Data Index: 551230 (The Pile)

Max Activating Token Index: 103

Text #7

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1855. Min Act: -0.0000

Data Index: 670239 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1648. Min Act: -0.0000

Data Index: 819423 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1466. Min Act: -0.0000

Data Index: 932132 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1623. Min Act: -0.0000

Data Index: 426100 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1577. Min Act: 0.0001

Data Index: 1631014 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1354730 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1300355 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1396815 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1263205 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1888665 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1776052 (The Pile)

Max Activating Token Index: 910

Text #18

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1031818 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1565. Min Act: 0.0000

Data Index: 756910 (The Pile)

Max Activating Token Index: 169