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

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

Neuron 3222 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0512. Min Act: -0.0000

Data Index: 988665 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0485. Min Act: -0.0000

Data Index: 20557 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0466. Min Act: -0.0000

Data Index: 637947 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1105174 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0457. Min Act: -0.0000

Data Index: 95791 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0451. Min Act: -0.0001

Data Index: 155189 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1064501 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0427. Min Act: -0.0000

Data Index: 737425 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0437. Min Act: -0.0000

Data Index: 881777 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0435. Min Act: -0.0000

Data Index: 71542 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0418. Min Act: -0.0000

Data Index: 1265309 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0414. Min Act: -0.0000

Data Index: 1334376 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1007973 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0407. Min Act: -0.0000

Data Index: 279505 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0389. Min Act: -0.0000

Data Index: 853901 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0388. Min Act: -0.0000

Data Index: 194960 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0389. Min Act: -0.0000

Data Index: 344238 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0402. Min Act: -0.0000

Data Index: 868521 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0357. Min Act: -0.0000

Data Index: 991060 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0368. Min Act: -0.0000

Data Index: 545633 (C4 (Web Text))

Max Activating Token Index: 354