Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 427 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1454. Min Act: -0.0001

Data Index: 895811 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1353. Min Act: -0.0001

Data Index: 742239 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1394. Min Act: -0.0001

Data Index: 395884 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1363. Min Act: -0.0001

Data Index: 1062114 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1384. Min Act: -0.0001

Data Index: 436247 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1030410 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1325. Min Act: -0.0001

Data Index: 522534 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1262. Min Act: -0.0001

Data Index: 427748 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1225. Min Act: -0.0000

Data Index: 788975 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1149570 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1001294 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1187811 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1235. Min Act: -0.0001

Data Index: 12506 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1069389 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1009240 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1312099 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1159. Min Act: -0.0001

Data Index: 837706 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1237. Min Act: -0.0001

Data Index: 921655 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1251. Min Act: -0.0001

Data Index: 536285 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1144. Min Act: -0.0001

Data Index: 802286 (C4 (Web Text))

Max Activating Token Index: 991