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

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

Neuron 3383 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1541. Min Act: -0.0001

Data Index: 398621 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1249. Min Act: -0.0001

Data Index: 985874 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1289. Min Act: -0.0000

Data Index: 498716 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1022601 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1102788 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1246. Min Act: -0.0000

Data Index: 877982 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1207. Min Act: -0.0000

Data Index: 398485 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1149. Min Act: -0.0001

Data Index: 629588 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1455833 (Python Code)

Max Activating Token Index: 977

Text #9

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1174. Min Act: -0.0000

Data Index: 1094644 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1200. Min Act: -0.0001

Data Index: 433293 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1017418 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1600279 (Python Code)

Max Activating Token Index: 162

Text #13

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1343892 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1091. Min Act: -0.0000

Data Index: 827910 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1522587 (Python Code)

Max Activating Token Index: 873

Text #16

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1120. Min Act: -0.0001

Data Index: 420659 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1162. Min Act: -0.0001

Data Index: 266590 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1115. Min Act: -0.0001

Data Index: 864754 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1283937 (C4 (Web Text))

Max Activating Token Index: 49