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

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

Neuron 100 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0399. Min Act: -0.0001

Data Index: 201580 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0328. Min Act: -0.0001

Data Index: 302433 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1600575 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1254081 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1647604 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1188408 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0310. Min Act: -0.0001

Data Index: 549930 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0294. Min Act: -0.0001

Data Index: 724258 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1207572 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1420502 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0284. Min Act: -0.0001

Data Index: 487786 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1149593 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0281. Min Act: -0.0001

Data Index: 174144 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0274. Min Act: -0.0001

Data Index: 109062 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0259. Min Act: -0.0001

Data Index: 954392 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1641123 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1100373 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0298. Min Act: -0.0001

Data Index: 986418 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0292. Min Act: -0.0001

Data Index: 617893 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0285. Min Act: -0.0001

Data Index: 843412 (C4 (Web Text))

Max Activating Token Index: 929