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

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

Neuron 2352 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: 0.1437. Min Range: -0.1437

Max Act: 0.1437. Min Act: -0.0001

Data Index: 729450 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1360349 (Python Code)

Max Activating Token Index: 732

Text #2

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1318. Min Act: -0.0001

Data Index: 872108 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1276. Min Act: -0.0001

Data Index: 967395 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1293954 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1371758 (Python Code)

Max Activating Token Index: 222

Text #6

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1185. Min Act: -0.0001

Data Index: 562583 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1053. Min Act: -0.0001

Data Index: 169539 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1342894 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1044267 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1199. Min Act: -0.0001

Data Index: 910993 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1084. Min Act: -0.0001

Data Index: 564002 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1142. Min Act: -0.0001

Data Index: 252232 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1431239 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1106435 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1143. Min Act: -0.0001

Data Index: 968432 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1021. Min Act: -0.0002

Data Index: 26897 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1080970 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.0971. Min Act: -0.0002

Data Index: 646814 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1328958 (C4 (Web Text))

Max Activating Token Index: 49