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

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

Neuron 51 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: 1.2379. Min Range: -1.2379

Max Act: 1.2379. Min Act: -0.0002

Data Index: 267249 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.2086. Min Act: -0.0002

Data Index: 365198 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.1695. Min Act: -0.0002

Data Index: 910423 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.1405. Min Act: -0.0002

Data Index: 870958 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.1126. Min Act: -0.0002

Data Index: 1270810 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0894. Min Act: -0.0002

Data Index: 654894 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.1060. Min Act: -0.0002

Data Index: 1221869 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0986. Min Act: -0.0002

Data Index: 463870 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0495. Min Act: -0.0002

Data Index: 882901 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0641. Min Act: -0.0002

Data Index: 540994 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0447. Min Act: -0.0002

Data Index: 1261925 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0434. Min Act: -0.0002

Data Index: 1240676 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0283. Min Act: -0.0002

Data Index: 77914 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0240. Min Act: -0.0002

Data Index: 578968 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0195. Min Act: -0.0002

Data Index: 1235534 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0377. Min Act: -0.0003

Data Index: 115391 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0196. Min Act: -0.0003

Data Index: 1224530 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0078. Min Act: -0.0002

Data Index: 104098 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0119. Min Act: -0.0002

Data Index: 1222404 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9996. Min Act: -0.0002

Data Index: 563494 (C4 (Web Text))

Max Activating Token Index: 592