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

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

Neuron 579 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1379. Min Act: -0.0001

Data Index: 913820 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1239. Min Act: -0.0001

Data Index: 20342 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1282. Min Act: -0.0000

Data Index: 864640 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1267. Min Act: -0.0000

Data Index: 66121 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1253. Min Act: -0.0000

Data Index: 717672 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1216. Min Act: -0.0000

Data Index: 193020 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1225. Min Act: -0.0000

Data Index: 120624 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1234. Min Act: -0.0001

Data Index: 300336 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1105. Min Act: -0.0000

Data Index: 938820 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1088396 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1151. Min Act: -0.0001

Data Index: 312216 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1058. Min Act: -0.0000

Data Index: 779623 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1046. Min Act: -0.0001

Data Index: 452791 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1059853 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1075. Min Act: -0.0000

Data Index: 694729 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1152. Min Act: -0.0001

Data Index: 248416 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1159. Min Act: -0.0000

Data Index: 785733 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1098. Min Act: -0.0001

Data Index: 178732 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1064. Min Act: -0.0001

Data Index: 203820 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0979. Min Act: -0.0000

Data Index: 14687 (C4 (Web Text))

Max Activating Token Index: 631