Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 922 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0004

Data Index: 1146936 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1057467 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0312. Min Act: -0.0004

Data Index: 619469 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1105494 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0302. Min Act: -0.0003

Data Index: 619246 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1295007 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0294. Min Act: -0.0003

Data Index: 224523 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0294. Min Act: -0.0003

Data Index: 639783 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0298. Min Act: -0.0003

Data Index: 729426 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1204561 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1240681 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0296. Min Act: -0.0004

Data Index: 979327 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0287. Min Act: -0.0003

Data Index: 606659 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1627414 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0289. Min Act: -0.0003

Data Index: 691138 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1018638 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0291. Min Act: -0.0003

Data Index: 760783 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0284. Min Act: -0.0003

Data Index: 234118 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0291. Min Act: -0.0003

Data Index: 620030 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0289. Min Act: -0.0004

Data Index: 744513 (C4 (Web Text))

Max Activating Token Index: 193