Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5774 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1374. Min Act: -0.0000

Data Index: 84846 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1389. Min Act: -0.0000

Data Index: 718515 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1329. Min Act: -0.0000

Data Index: 16069 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1323. Min Act: -0.0000

Data Index: 620141 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1223. Min Act: -0.0000

Data Index: 1646867 (Python Code)

Max Activating Token Index: 902

Text #5

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1075032 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1505592 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1185. Min Act: -0.0000

Data Index: 741159 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1613498 (Python Code)

Max Activating Token Index: 1006

Text #9

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1141. Min Act: -0.0000

Data Index: 758152 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1434079 (Python Code)

Max Activating Token Index: 267

Text #11

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1467952 (Python Code)

Max Activating Token Index: 450

Text #12

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1553294 (Python Code)

Max Activating Token Index: 612

Text #13

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1085. Min Act: -0.0000

Data Index: 514625 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1203. Min Act: -0.0000

Data Index: 130564 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1115. Min Act: -0.0000

Data Index: 820187 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1067. Min Act: -0.0000

Data Index: 81025 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1068. Min Act: -0.0000

Data Index: 847986 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1532156 (Python Code)

Max Activating Token Index: 546

Text #19

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1092. Min Act: -0.0000

Data Index: 164874 (C4 (Web Text))

Max Activating Token Index: 1006