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

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

Neuron 4066 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0579. Min Act: -0.0001

Data Index: 701436 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1007613 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0623. Min Act: -0.0001

Data Index: 151172 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1036993 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1166091 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0500. Min Act: -0.0001

Data Index: 242445 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0459. Min Act: -0.0001

Data Index: 369940 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0389. Min Act: -0.0001

Data Index: 1007181 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0457. Min Act: -0.0001

Data Index: 251939 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0470. Min Act: -0.0001

Data Index: 965887 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0427. Min Act: -0.0001

Data Index: 262197 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0444. Min Act: -0.0001

Data Index: 653944 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0392. Min Act: -0.0001

Data Index: 201280 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1337441 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0444. Min Act: -0.0001

Data Index: 384303 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1107257 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0352. Min Act: -0.0001

Data Index: 891381 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0417. Min Act: -0.0001

Data Index: 4673 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1341421 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0422. Min Act: -0.0001

Data Index: 1235605 (C4 (Web Text))

Max Activating Token Index: 466