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

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

Neuron 1994 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: 0.1486. Min Range: -0.1486

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1329944 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1361. Min Act: -0.0001

Data Index: 79310 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1089063 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1280. Min Act: -0.0001

Data Index: 1192511 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1189. Min Act: -0.0001

Data Index: 697373 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1139. Min Act: -0.0002

Data Index: 355295 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1191. Min Act: -0.0002

Data Index: 1244096 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1136. Min Act: -0.0001

Data Index: 627289 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1456. Min Act: -0.0002

Data Index: 1311244 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1130. Min Act: -0.0001

Data Index: 478220 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1116. Min Act: -0.0001

Data Index: 597406 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1097. Min Act: -0.0001

Data Index: 512500 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1071. Min Act: -0.0002

Data Index: 624415 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1225. Min Act: -0.0002

Data Index: 324738 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1016567 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1208. Min Act: -0.0002

Data Index: 1082108 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1044. Min Act: -0.0001

Data Index: 167999 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1060. Min Act: -0.0001

Data Index: 359881 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1574680 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1138. Min Act: -0.0001

Data Index: 335310 (C4 (Web Text))

Max Activating Token Index: 278