Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 360 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.9184. Min Act: -0.0000

Data Index: 864354 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 3.0369. Min Range: -3.0369

Max Act: 3.0369. Min Act: -0.0000

Data Index: 258146 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.9726. Min Act: -0.0000

Data Index: 750154 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8306. Min Act: -0.0000

Data Index: 402125 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.9524. Min Act: 0.0000

Data Index: 579092 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8509. Min Act: -0.0000

Data Index: 916513 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.6912. Min Act: -0.0000

Data Index: 283066 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8247. Min Act: -0.0000

Data Index: 782979 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8838. Min Act: -0.0000

Data Index: 816699 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.6343. Min Act: -0.0000

Data Index: 1287514 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8372. Min Act: -0.0000

Data Index: 1281148 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8490. Min Act: -0.0000

Data Index: 1253710 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.6948. Min Act: -0.0000

Data Index: 233189 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.5580. Min Act: -0.0000

Data Index: 380061 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.6888. Min Act: 0.0000

Data Index: 1026222 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.6655. Min Act: -0.0000

Data Index: 1069949 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.6541. Min Act: -0.0000

Data Index: 327295 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.7666. Min Act: -0.0000

Data Index: 1101097 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.6287. Min Act: -0.0000

Data Index: 962645 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.6068. Min Act: 0.0000

Data Index: 1150385 (C4 (Web Text))

Max Activating Token Index: 920