Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5804 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1749. Min Act: -0.0001

Data Index: 819200 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1467. Min Act: -0.0001

Data Index: 677 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1326. Min Act: -0.0001

Data Index: 47986 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1449. Min Act: -0.0001

Data Index: 161929 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1261. Min Act: -0.0001

Data Index: 858833 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1166. Min Act: -0.0001

Data Index: 410570 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1237. Min Act: -0.0002

Data Index: 23308 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1143. Min Act: -0.0001

Data Index: 658838 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1232. Min Act: -0.0001

Data Index: 756227 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1185. Min Act: -0.0001

Data Index: 881385 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1163623 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1114. Min Act: -0.0001

Data Index: 959309 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1172. Min Act: -0.0001

Data Index: 742828 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1181. Min Act: -0.0001

Data Index: 214629 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1335. Min Act: -0.0001

Data Index: 568876 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1224. Min Act: -0.0001

Data Index: 779955 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1240510 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1291741 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1188986 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1170. Min Act: -0.0001

Data Index: 899732 (C4 (Web Text))

Max Activating Token Index: 923