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

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

Neuron 2613 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1557. Min Act: -0.0002

Data Index: 347367 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1471. Min Act: -0.0002

Data Index: 213707 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1423. Min Act: -0.0002

Data Index: 621100 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1299. Min Act: -0.0002

Data Index: 1082783 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1482. Min Act: -0.0002

Data Index: 118095 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1252. Min Act: -0.0002

Data Index: 72483 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1096925 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1427. Min Act: -0.0002

Data Index: 1169496 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1278881 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1314. Min Act: -0.0001

Data Index: 783846 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1272. Min Act: -0.0001

Data Index: 555230 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1224. Min Act: -0.0002

Data Index: 634695 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1406. Min Act: -0.0002

Data Index: 914623 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1179. Min Act: -0.0002

Data Index: 20353 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1174. Min Act: -0.0002

Data Index: 809703 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1221. Min Act: -0.0001

Data Index: 932250 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1138. Min Act: -0.0001

Data Index: 577952 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1230. Min Act: -0.0001

Data Index: 657120 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1329. Min Act: -0.0002

Data Index: 18700 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1147. Min Act: -0.0002

Data Index: 409708 (C4 (Web Text))

Max Activating Token Index: 414