Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 992 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.1937. Min Act: -0.0000

Data Index: 423117 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.2459. Min Act: -0.0000

Data Index: 410386 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.2362. Min Act: -0.0000

Data Index: 755868 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.2056. Min Act: -0.0000

Data Index: 569566 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1032694 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.1303. Min Act: -0.0000

Data Index: 1069480 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.1216. Min Act: -0.0000

Data Index: 431503 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.1161. Min Act: -0.0000

Data Index: 1293247 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.0378. Min Act: -0.0000

Data Index: 587502 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.0214. Min Act: -0.0000

Data Index: 217204 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.0529. Min Act: -0.0000

Data Index: 434966 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.0400. Min Act: -0.0000

Data Index: 219178 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.0953. Min Act: -0.0000

Data Index: 143133 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.0487. Min Act: 0.0000

Data Index: 236002 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.0069. Min Act: -0.0000

Data Index: 386019 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.0246. Min Act: 0.0000

Data Index: 150628 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.9856. Min Act: 0.0000

Data Index: 201066 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.9334. Min Act: -0.0000

Data Index: 580798 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.9818. Min Act: -0.0000

Data Index: 746168 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1267938 (C4 (Web Text))

Max Activating Token Index: 59