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

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

Neuron 2041 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: 1.4414. Min Range: -1.4414

Max Act: 1.4414. Min Act: -0.0000

Data Index: 574397 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.0953. Min Act: -0.0000

Data Index: 363086 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.0459. Min Act: -0.0000

Data Index: 71386 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.0519. Min Act: -0.0000

Data Index: 53542 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.9798. Min Act: -0.0000

Data Index: 218367 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1085340 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1043867 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1054161 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.9462. Min Act: -0.0000

Data Index: 989746 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1220930 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.9332. Min Act: -0.0000

Data Index: 327519 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1040772 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.8891. Min Act: -0.0000

Data Index: 582528 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1269399 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.8484. Min Act: -0.0000

Data Index: 916197 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1033172 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1024914 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.8107. Min Act: -0.0000

Data Index: 353176 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1095530 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.7037. Min Act: -0.0000

Data Index: 466009 (C4 (Web Text))

Max Activating Token Index: 674