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

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

Neuron 3312 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1392. Min Act: -0.0001

Data Index: 962905 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1344222 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1276. Min Act: -0.0001

Data Index: 39559 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1047995 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1200. Min Act: -0.0001

Data Index: 931200 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1202. Min Act: -0.0001

Data Index: 586577 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1192. Min Act: -0.0001

Data Index: 110809 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1246157 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1200. Min Act: -0.0001

Data Index: 283995 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1283. Min Act: -0.0001

Data Index: 974089 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1252. Min Act: -0.0001

Data Index: 187205 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1154. Min Act: -0.0001

Data Index: 427839 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1192. Min Act: -0.0001

Data Index: 549357 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1234921 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1151. Min Act: -0.0001

Data Index: 223760 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1080. Min Act: -0.0001

Data Index: 245574 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1095. Min Act: -0.0001

Data Index: 34423 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1103. Min Act: -0.0001

Data Index: 281697 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1054. Min Act: -0.0001

Data Index: 872744 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1077. Min Act: -0.0001

Data Index: 902760 (C4 (Web Text))

Max Activating Token Index: 433