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

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

Neuron 4016 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2362. Min Act: -0.0001

Data Index: 1111684 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2119. Min Act: -0.0000

Data Index: 797001 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1879. Min Act: -0.0001

Data Index: 378125 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2033. Min Act: -0.0001

Data Index: 413269 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1720. Min Act: -0.0001

Data Index: 9761 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1514. Min Act: -0.0000

Data Index: 180848 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1436. Min Act: -0.0001

Data Index: 876847 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1333. Min Act: -0.0001

Data Index: 654673 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1063682 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1316. Min Act: -0.0000

Data Index: 240990 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1300. Min Act: -0.0001

Data Index: 190836 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1235. Min Act: -0.0000

Data Index: 329653 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1277697 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1252. Min Act: -0.0001

Data Index: 689397 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1149. Min Act: -0.0000

Data Index: 814857 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1359. Min Act: -0.0000

Data Index: 557803 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1176. Min Act: -0.0001

Data Index: 774399 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1066583 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1134. Min Act: -0.0001

Data Index: 662015 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1021. Min Act: -0.0000

Data Index: 843342 (C4 (Web Text))

Max Activating Token Index: 282