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

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

Neuron 1789 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2658. Min Act: -0.0000

Data Index: 871601 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2500. Min Act: -0.0000

Data Index: 369448 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1340430 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2311. Min Act: -0.0000

Data Index: 747646 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2367. Min Act: -0.0000

Data Index: 246192 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2362. Min Act: -0.0000

Data Index: 883599 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2335. Min Act: -0.0000

Data Index: 144602 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2486. Min Act: -0.0000

Data Index: 754282 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2416. Min Act: -0.0000

Data Index: 860667 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1165486 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2150. Min Act: -0.0000

Data Index: 32147 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2191. Min Act: -0.0000

Data Index: 912862 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1640981 (Python Code)

Max Activating Token Index: 751

Text #13

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2181. Min Act: -0.0000

Data Index: 827164 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1277693 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2093. Min Act: -0.0000

Data Index: 802876 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2237. Min Act: -0.0000

Data Index: 264073 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2063. Min Act: -0.0000

Data Index: 105549 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1379444 (Python Code)

Max Activating Token Index: 966

Text #19

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2152. Min Act: -0.0000

Data Index: 433582 (C4 (Web Text))

Max Activating Token Index: 425