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

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

Neuron 5496 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1622. Min Act: -0.0002

Data Index: 757179 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1516. Min Act: -0.0001

Data Index: 765833 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1296. Min Act: -0.0001

Data Index: 943984 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1447. Min Act: -0.0001

Data Index: 852747 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1127. Min Act: -0.0001

Data Index: 379780 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1426. Min Act: -0.0001

Data Index: 695437 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1440. Min Act: -0.0001

Data Index: 144007 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1383. Min Act: -0.0001

Data Index: 416288 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1333. Min Act: -0.0001

Data Index: 750131 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1279. Min Act: -0.0001

Data Index: 16395 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1254. Min Act: -0.0001

Data Index: 593356 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1179. Min Act: -0.0001

Data Index: 651772 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1399. Min Act: -0.0001

Data Index: 420502 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1381. Min Act: -0.0001

Data Index: 955931 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1162. Min Act: -0.0001

Data Index: 725319 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1285. Min Act: -0.0001

Data Index: 580991 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1271997 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1198. Min Act: -0.0001

Data Index: 705448 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1264. Min Act: -0.0001

Data Index: 337205 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1168. Min Act: -0.0001

Data Index: 253408 (C4 (Web Text))

Max Activating Token Index: 391