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

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

Neuron 3652 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1317356 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1427. Min Act: -0.0001

Data Index: 234913 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1520773 (Python Code)

Max Activating Token Index: 101

Text #3

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1351. Min Act: -0.0001

Data Index: 1325112 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1613230 (Python Code)

Max Activating Token Index: 855

Text #5

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1347. Min Act: -0.0001

Data Index: 257693 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1419276 (Python Code)

Max Activating Token Index: 924

Text #7

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1552349 (Python Code)

Max Activating Token Index: 544

Text #8

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1145. Min Act: -0.0001

Data Index: 471299 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1165. Min Act: -0.0001

Data Index: 720545 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1575633 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1245414 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1153528 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1123660 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1440595 (Python Code)

Max Activating Token Index: 140

Text #15

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1130. Min Act: -0.0001

Data Index: 855030 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1653034 (Python Code)

Max Activating Token Index: 396

Text #17

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1100. Min Act: -0.0001

Data Index: 774179 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1406594 (Python Code)

Max Activating Token Index: 934

Text #19

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1091. Min Act: -0.0001

Data Index: 964558 (C4 (Web Text))

Max Activating Token Index: 177