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

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

Neuron 4444 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: 0.1411. Min Range: -0.1411

Max Act: 0.1411. Min Act: -0.0001

Data Index: 315895 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1294. Min Act: -0.0001

Data Index: 795267 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1111142 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1327. Min Act: -0.0001

Data Index: 657562 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1177. Min Act: -0.0001

Data Index: 28762 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1338. Min Act: -0.0001

Data Index: 157605 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1195991 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1150. Min Act: -0.0001

Data Index: 385330 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1254. Min Act: -0.0001

Data Index: 914974 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1101602 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1154001 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1199. Min Act: -0.0001

Data Index: 423623 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1159. Min Act: -0.0001

Data Index: 304076 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1136. Min Act: -0.0001

Data Index: 80645 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1251. Min Act: -0.0001

Data Index: 306353 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1173. Min Act: -0.0001

Data Index: 504844 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1331. Min Act: -0.0001

Data Index: 193057 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1155. Min Act: -0.0001

Data Index: 728949 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1028814 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1034. Min Act: -0.0001

Data Index: 906200 (C4 (Web Text))

Max Activating Token Index: 884