Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4534 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9359. Min Range: -2.9359

Max Act: 2.9359. Min Act: 0.0000

Data Index: 894934 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 2.9359. Min Range: -2.9359

Max Act: 2.3923. Min Act: -0.0000

Data Index: 802159 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 2.9359. Min Range: -2.9359

Max Act: 2.3611. Min Act: -0.0000

Data Index: 261903 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 2.9359. Min Range: -2.9359

Max Act: 2.1764. Min Act: -0.0000

Data Index: 869666 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.8368. Min Act: -0.0000

Data Index: 774922 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.8624. Min Act: -0.0000

Data Index: 1131644 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.8444. Min Act: -0.0000

Data Index: 1295083 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.7317. Min Act: 0.0000

Data Index: 550160 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.7040. Min Act: -0.0000

Data Index: 1253354 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.6891. Min Act: -0.0000

Data Index: 639921 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.5802. Min Act: -0.0000

Data Index: 667190 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.6278. Min Act: -0.0000

Data Index: 742353 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.6256. Min Act: -0.0000

Data Index: 690570 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.6820. Min Act: -0.0000

Data Index: 975979 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1357931 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.6471. Min Act: -0.0000

Data Index: 475090 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.6287. Min Act: -0.0000

Data Index: 828771 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.5312. Min Act: -0.0000

Data Index: 1266244 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.5407. Min Act: 0.0000

Data Index: 287523 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 2.9359. Min Range: -2.9359

Max Act: 1.5199. Min Act: -0.0000

Data Index: 941282 (C4 (Web Text))

Max Activating Token Index: 133