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

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

Neuron 3499 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1745. Min Act: -0.0001

Data Index: 865344 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1055493 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1669. Min Act: -0.0001

Data Index: 1272332 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1466. Min Act: -0.0001

Data Index: 34181 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1573. Min Act: -0.0001

Data Index: 914836 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1184. Min Act: -0.0001

Data Index: 1336480 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1324. Min Act: -0.0001

Data Index: 945526 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1310. Min Act: -0.0001

Data Index: 221758 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1415. Min Act: -0.0001

Data Index: 327016 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1302. Min Act: -0.0001

Data Index: 869999 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1280. Min Act: -0.0001

Data Index: 176973 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1268. Min Act: -0.0001

Data Index: 309629 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1219. Min Act: -0.0001

Data Index: 834777 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1134. Min Act: -0.0001

Data Index: 663714 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1135. Min Act: -0.0001

Data Index: 273192 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1085081 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1155795 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1243. Min Act: -0.0001

Data Index: 817536 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1093604 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1239. Min Act: -0.0001

Data Index: 2204 (C4 (Web Text))

Max Activating Token Index: 290