Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3916 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1555. Min Act: -0.0000

Data Index: 752143 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1514. Min Act: -0.0000

Data Index: 922356 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1149331 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1400. Min Act: -0.0000

Data Index: 1075232 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1293. Min Act: -0.0001

Data Index: 82906 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1014138 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1239. Min Act: -0.0000

Data Index: 958493 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1279. Min Act: -0.0000

Data Index: 755712 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1280. Min Act: -0.0000

Data Index: 60992 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1317. Min Act: -0.0001

Data Index: 573154 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1065485 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1187. Min Act: -0.0000

Data Index: 775148 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1237. Min Act: -0.0000

Data Index: 176626 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1212. Min Act: -0.0000

Data Index: 839075 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1164. Min Act: -0.0000

Data Index: 94421 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1158. Min Act: -0.0001

Data Index: 646936 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1277. Min Act: -0.0000

Data Index: 685680 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1183. Min Act: -0.0000

Data Index: 324379 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1200. Min Act: -0.0001

Data Index: 888649 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1224. Min Act: -0.0000

Data Index: 378407 (C4 (Web Text))

Max Activating Token Index: 99