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

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

Neuron 5337 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: 0.1452. Min Range: -0.1452

Max Act: 0.1452. Min Act: -0.0002

Data Index: 289617 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1417. Min Act: -0.0002

Data Index: 39359 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1378. Min Act: -0.0002

Data Index: 1559533 (Python Code)

Max Activating Token Index: 100

Text #3

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1348. Min Act: -0.0002

Data Index: 1261124 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1360. Min Act: -0.0002

Data Index: 418394 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1355. Min Act: -0.0002

Data Index: 1247158 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1320. Min Act: -0.0002

Data Index: 672025 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1231. Min Act: -0.0002

Data Index: 1082426 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1225. Min Act: -0.0002

Data Index: 1370130 (Python Code)

Max Activating Token Index: 884

Text #9

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1208. Min Act: -0.0002

Data Index: 716924 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1631383 (Python Code)

Max Activating Token Index: 547

Text #11

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1186. Min Act: -0.0002

Data Index: 290047 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1178. Min Act: -0.0002

Data Index: 500891 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1170. Min Act: -0.0002

Data Index: 1317176 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1183. Min Act: -0.0002

Data Index: 712652 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1429959 (Python Code)

Max Activating Token Index: 447

Text #16

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1156. Min Act: -0.0002

Data Index: 822473 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1159. Min Act: -0.0002

Data Index: 400660 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1175. Min Act: -0.0002

Data Index: 494293 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1373014 (Python Code)

Max Activating Token Index: 30