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

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

Neuron 4111 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: 0.1386. Min Range: -0.1386

Max Act: 0.1246. Min Act: -0.0001

Data Index: 734059 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1097343 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1299. Min Act: -0.0001

Data Index: 98336 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1260. Min Act: -0.0001

Data Index: 374218 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1141. Min Act: -0.0001

Data Index: 867797 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1261. Min Act: -0.0001

Data Index: 712624 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1149. Min Act: -0.0001

Data Index: 111014 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1267. Min Act: -0.0001

Data Index: 426273 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1531217 (Python Code)

Max Activating Token Index: 675

Text #9

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1194. Min Act: -0.0001

Data Index: 732602 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1104. Min Act: -0.0001

Data Index: 676719 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1100. Min Act: -0.0001

Data Index: 770773 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0993. Min Act: -0.0000

Data Index: 233915 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1058. Min Act: -0.0001

Data Index: 535181 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1042. Min Act: -0.0000

Data Index: 901506 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1033. Min Act: -0.0001

Data Index: 795211 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1312954 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1072. Min Act: -0.0001

Data Index: 846152 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1277741 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1050. Min Act: -0.0001

Data Index: 241699 (C4 (Web Text))

Max Activating Token Index: 446