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

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

Neuron 492 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: 0.1607. Min Range: -0.1607

Max Act: 0.1607. Min Act: -0.0001

Data Index: 1206532 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1283886 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1331. Min Act: -0.0001

Data Index: 347946 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1313. Min Act: -0.0001

Data Index: 179171 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1284. Min Act: -0.0001

Data Index: 205403 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1341879 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1143. Min Act: -0.0001

Data Index: 973894 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1142. Min Act: -0.0001

Data Index: 893748 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1209. Min Act: -0.0001

Data Index: 341345 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1200. Min Act: -0.0001

Data Index: 289725 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1237962 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1052117 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1193. Min Act: -0.0001

Data Index: 229931 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1089. Min Act: -0.0001

Data Index: 819123 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1176812 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1121. Min Act: -0.0001

Data Index: 878646 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1205. Min Act: -0.0001

Data Index: 64098 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1242477 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1165. Min Act: -0.0001

Data Index: 882100 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1017. Min Act: -0.0001

Data Index: 831044 (C4 (Web Text))

Max Activating Token Index: 530