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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2653 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2668. Min Range: -2.2668

Max Act: 2.2668. Min Act: 0.0000

Data Index: 1402398 (Python Code)

Max Activating Token Index: 653

Text #1

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.7732. Min Act: -0.0000

Data Index: 1631160 (Python Code)

Max Activating Token Index: 195

Text #2

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.5825. Min Act: -0.0000

Data Index: 808586 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.4317. Min Act: -0.0000

Data Index: 1508509 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.4094. Min Act: -0.0000

Data Index: 1625329 (Python Code)

Max Activating Token Index: 155

Text #5

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.2652. Min Act: -0.0000

Data Index: 1586397 (Python Code)

Max Activating Token Index: 288

Text #6

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.1264. Min Act: -0.0000

Data Index: 229124 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.1793. Min Act: -0.0000

Data Index: 980007 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.1860. Min Act: -0.0000

Data Index: 1385980 (Python Code)

Max Activating Token Index: 863

Text #9

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.1776. Min Act: -0.0000

Data Index: 469337 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.0729. Min Act: -0.0000

Data Index: 1013473 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.0534. Min Act: -0.0000

Data Index: 638979 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1460390 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1485081 (Python Code)

Max Activating Token Index: 525

Text #14

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1113217 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.0236. Min Act: -0.0000

Data Index: 1439231 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1557229 (Python Code)

Max Activating Token Index: 849

Text #17

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.0162. Min Act: -0.0000

Data Index: 1271398 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 2.2668. Min Range: -2.2668

Max Act: 1.0062. Min Act: -0.0000

Data Index: 672177 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 2.2668. Min Range: -2.2668

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1278973 (C4 (Web Text))

Max Activating Token Index: 890