Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 176 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0003

Data Index: 442041 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0602. Min Act: -0.0002

Data Index: 177411 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0606. Min Act: -0.0002

Data Index: 102879 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1143723 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0513. Min Act: -0.0002

Data Index: 409705 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0503. Min Act: -0.0002

Data Index: 125981 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0466. Min Act: -0.0003

Data Index: 76655 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0463. Min Act: -0.0002

Data Index: 754551 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0452. Min Act: -0.0002

Data Index: 631720 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0451. Min Act: -0.0003

Data Index: 386939 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0428. Min Act: -0.0003

Data Index: 307913 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0426. Min Act: -0.0003

Data Index: 658027 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0423. Min Act: -0.0002

Data Index: 551403 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0421. Min Act: -0.0002

Data Index: 184214 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0417. Min Act: -0.0003

Data Index: 892057 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0397. Min Act: -0.0002

Data Index: 649759 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0394. Min Act: -0.0003

Data Index: 371449 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1049452 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0384. Min Act: -0.0003

Data Index: 306400 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1012052 (C4 (Web Text))

Max Activating Token Index: 991