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

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

Neuron 1650 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: 0.0623. Min Range: -0.0623

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1483475 (Python Code)

Max Activating Token Index: 537

Text #1

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0469. Min Act: -0.0003

Data Index: 442341 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1053911 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0456. Min Act: -0.0004

Data Index: 1578345 (Python Code)

Max Activating Token Index: 244

Text #4

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0459. Min Act: -0.0003

Data Index: 587041 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0433. Min Act: -0.0003

Data Index: 345948 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0420. Min Act: -0.0003

Data Index: 968830 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0428. Min Act: -0.0004

Data Index: 1371339 (Python Code)

Max Activating Token Index: 651

Text #8

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0421. Min Act: -0.0004

Data Index: 812380 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1234972 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0412. Min Act: -0.0004

Data Index: 1173157 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1328735 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0421. Min Act: -0.0004

Data Index: 1166827 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0413. Min Act: -0.0003

Data Index: 403511 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0418. Min Act: -0.0003

Data Index: 28269 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0407. Min Act: -0.0003

Data Index: 323037 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0405. Min Act: -0.0003

Data Index: 553061 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1044932 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1182493 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1486249 (Python Code)

Max Activating Token Index: 923