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

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

Neuron 4696 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: 0.0455. Min Range: -0.0455

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1382083 (Python Code)

Max Activating Token Index: 829

Text #1

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0405. Min Act: -0.0002

Data Index: 85005 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1475522 (Python Code)

Max Activating Token Index: 561

Text #3

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1186768 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1162765 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0420. Min Act: -0.0002

Data Index: 563591 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1534658 (Python Code)

Max Activating Token Index: 324

Text #7

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0403. Min Act: -0.0002

Data Index: 933871 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0409. Min Act: -0.0002

Data Index: 82189 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0407. Min Act: -0.0002

Data Index: 755600 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1030429 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0405. Min Act: -0.0002

Data Index: 979484 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0425. Min Act: -0.0002

Data Index: 963680 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0396. Min Act: -0.0002

Data Index: 329449 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0355. Min Act: -0.0002

Data Index: 663235 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0405. Min Act: -0.0002

Data Index: 99591 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1067094 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0393. Min Act: -0.0002

Data Index: 892527 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0371. Min Act: -0.0002

Data Index: 854568 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0414. Min Act: -0.0002

Data Index: 767502 (C4 (Web Text))

Max Activating Token Index: 349