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

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

Neuron 3484 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: 0.1679. Min Range: -0.1679

Max Act: 0.1612. Min Act: -0.0000

Data Index: 709178 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1679. Min Act: -0.0001

Data Index: 308763 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1170609 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1433. Min Act: -0.0001

Data Index: 245828 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1407. Min Act: -0.0001

Data Index: 234050 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1401. Min Act: -0.0000

Data Index: 128023 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1301. Min Act: -0.0000

Data Index: 763564 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1337. Min Act: -0.0000

Data Index: 100481 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1321. Min Act: -0.0001

Data Index: 609550 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1442850 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1327392 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1311979 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1192. Min Act: -0.0000

Data Index: 813869 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1238. Min Act: -0.0000

Data Index: 334240 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1601412 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1210416 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1138333 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1199. Min Act: -0.0001

Data Index: 735625 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1238545 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1192. Min Act: -0.0000

Data Index: 629132 (C4 (Web Text))

Max Activating Token Index: 785