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

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

Neuron 2646 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0002

Data Index: 80358 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0523. Min Act: -0.0002

Data Index: 405888 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0441. Min Act: -0.0002

Data Index: 913815 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0482. Min Act: -0.0002

Data Index: 455369 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0469. Min Act: -0.0002

Data Index: 422938 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0505. Min Act: -0.0002

Data Index: 860796 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0458. Min Act: -0.0002

Data Index: 73545 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0425. Min Act: -0.0002

Data Index: 588702 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0413. Min Act: -0.0002

Data Index: 586306 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0401. Min Act: -0.0002

Data Index: 248502 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0391. Min Act: -0.0002

Data Index: 635283 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1007445 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0384. Min Act: -0.0002

Data Index: 995009 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0389. Min Act: -0.0002

Data Index: 768914 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0367. Min Act: -0.0002

Data Index: 955171 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1327413 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0415. Min Act: -0.0002

Data Index: 555559 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0366. Min Act: -0.0002

Data Index: 991479 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1164211 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1081751 (C4 (Web Text))

Max Activating Token Index: 263