Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 602 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1885. Min Act: -0.0001

Data Index: 6859 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1925. Min Act: -0.0001

Data Index: 720798 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1586. Min Act: -0.0001

Data Index: 829317 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1776. Min Act: -0.0001

Data Index: 186412 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1726. Min Act: -0.0001

Data Index: 894021 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1618. Min Act: -0.0001

Data Index: 653501 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1633. Min Act: -0.0001

Data Index: 574518 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1621. Min Act: -0.0001

Data Index: 1188508 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1614. Min Act: -0.0001

Data Index: 338726 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1283584 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1539. Min Act: -0.0001

Data Index: 671450 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1518. Min Act: -0.0001

Data Index: 37946 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1343639 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1519. Min Act: -0.0001

Data Index: 216837 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1004271 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1390. Min Act: -0.0001

Data Index: 146524 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1421. Min Act: -0.0001

Data Index: 26662 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1206260 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1313098 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1337. Min Act: -0.0001

Data Index: 1160835 (C4 (Web Text))

Max Activating Token Index: 950