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

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

Neuron 2604 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1250043 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1883. Min Act: -0.0001

Data Index: 815199 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1004860 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1761. Min Act: -0.0001

Data Index: 393437 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1805. Min Act: -0.0000

Data Index: 605250 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1300604 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1365. Min Act: -0.0001

Data Index: 800522 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1165708 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1234. Min Act: -0.0001

Data Index: 949369 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1293. Min Act: -0.0001

Data Index: 146447 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1051. Min Act: -0.0001

Data Index: 240681 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1198. Min Act: -0.0001

Data Index: 654008 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1206. Min Act: -0.0001

Data Index: 693659 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1184. Min Act: -0.0001

Data Index: 560148 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1235. Min Act: -0.0001

Data Index: 712788 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1222. Min Act: -0.0001

Data Index: 1338675 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1258. Min Act: -0.0001

Data Index: 56818 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1210. Min Act: -0.0001

Data Index: 39646 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1137. Min Act: -0.0001

Data Index: 629196 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1218. Min Act: -0.0001

Data Index: 990323 (C4 (Web Text))

Max Activating Token Index: 586