Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1487 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0623. Min Act: -0.0002

Data Index: 148741 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1478106 (Python Code)

Max Activating Token Index: 1003

Text #2

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1362626 (Python Code)

Max Activating Token Index: 216

Text #3

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0577. Min Act: -0.0001

Data Index: 335974 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0537. Min Act: -0.0001

Data Index: 484239 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0569. Min Act: -0.0001

Data Index: 313986 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0521. Min Act: -0.0001

Data Index: 644277 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1224183 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0486. Min Act: -0.0001

Data Index: 299517 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0539. Min Act: -0.0001

Data Index: 112385 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1349494 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0478. Min Act: -0.0001

Data Index: 808834 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1346739 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1488198 (Python Code)

Max Activating Token Index: 229

Text #14

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1244699 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0462. Min Act: -0.0001

Data Index: 1043925 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0428. Min Act: -0.0001

Data Index: 61961 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0466. Min Act: -0.0001

Data Index: 99870 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0459. Min Act: -0.0001

Data Index: 419438 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0450. Min Act: -0.0000

Data Index: 194359 (C4 (Web Text))

Max Activating Token Index: 772