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

Dataset: The Pile

Neuron 280 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: 1.0532. Min Range: -1.0532

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1973007 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 1.0532. Min Range: -1.0532

Max Act: 1.0532. Min Act: -0.0000

Data Index: 1520030 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9867. Min Act: -0.0000

Data Index: 963497 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 1.0532. Min Range: -1.0532

Max Act: 1.0349. Min Act: -0.0000

Data Index: 1032486 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8781. Min Act: -0.0000

Data Index: 333309 (The Pile)

Max Activating Token Index: 503

Text #5

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1296577 (The Pile)

Max Activating Token Index: 811

Text #6

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1935781 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1546091 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8776. Min Act: -0.0000

Data Index: 716378 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8119. Min Act: -0.0000

Data Index: 894360 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1792047 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1417529 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1155625 (The Pile)

Max Activating Token Index: 487

Text #13

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1004678 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1253520 (The Pile)

Max Activating Token Index: 921

Text #15

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1022074 (The Pile)

Max Activating Token Index: 940

Text #16

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9250. Min Act: -0.0000

Data Index: 549143 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1011164 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1646211 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1518209 (The Pile)

Max Activating Token Index: 646