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

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

Neuron 3080 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1659. Min Act: -0.0000

Data Index: 989775 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1431. Min Act: 0.0000

Data Index: 341740 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1347. Min Act: -0.0000

Data Index: 643589 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1389. Min Act: 0.0000

Data Index: 3611 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1420754 (Python Code)

Max Activating Token Index: 849

Text #5

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1277. Min Act: -0.0000

Data Index: 951693 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1241330 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1242. Min Act: -0.0000

Data Index: 707058 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1229. Min Act: -0.0000

Data Index: 322104 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1331. Min Act: -0.0000

Data Index: 446084 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1271. Min Act: -0.0000

Data Index: 144740 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1172. Min Act: -0.0000

Data Index: 736629 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1027924 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1162. Min Act: -0.0000

Data Index: 69798 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1320518 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1122062 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1270728 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1577599 (Python Code)

Max Activating Token Index: 763

Text #18

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1354925 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1142. Min Act: 0.0000

Data Index: 550640 (C4 (Web Text))

Max Activating Token Index: 223