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

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

Neuron 658 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1658. Min Act: -0.0002

Data Index: 1345881 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1486. Min Act: -0.0002

Data Index: 566740 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1456. Min Act: -0.0002

Data Index: 1302074 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1464. Min Act: -0.0002

Data Index: 790530 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1354. Min Act: -0.0002

Data Index: 1259325 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1306. Min Act: -0.0003

Data Index: 743862 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1304. Min Act: -0.0002

Data Index: 130065 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1281. Min Act: -0.0002

Data Index: 393634 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1231. Min Act: -0.0002

Data Index: 1123112 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1207. Min Act: -0.0003

Data Index: 917947 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1218. Min Act: -0.0003

Data Index: 164381 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1209. Min Act: -0.0002

Data Index: 155240 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1175. Min Act: -0.0002

Data Index: 1177858 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1190. Min Act: -0.0002

Data Index: 760428 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1192. Min Act: -0.0002

Data Index: 1599610 (Python Code)

Max Activating Token Index: 360

Text #15

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1153. Min Act: -0.0002

Data Index: 373568 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1135. Min Act: -0.0002

Data Index: 499980 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1611063 (Python Code)

Max Activating Token Index: 80

Text #18

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1656002 (Python Code)

Max Activating Token Index: 192

Text #19

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1126. Min Act: -0.0002

Data Index: 1153120 (C4 (Web Text))

Max Activating Token Index: 85