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

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

Neuron 2558 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1614702 (Python Code)

Max Activating Token Index: 926

Text #1

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1055518 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1581154 (Python Code)

Max Activating Token Index: 804

Text #3

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1296590 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1299354 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1434536 (Python Code)

Max Activating Token Index: 936

Text #6

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0374. Min Act: -0.0001

Data Index: 202886 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0349. Min Act: -0.0001

Data Index: 406572 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0348. Min Act: -0.0001

Data Index: 135748 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1561017 (Python Code)

Max Activating Token Index: 988

Text #10

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0318. Min Act: -0.0001

Data Index: 748377 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1073809 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1155971 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1280790 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1158908 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0305. Min Act: -0.0001

Data Index: 762746 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0311. Min Act: -0.0001

Data Index: 544833 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0304. Min Act: -0.0001

Data Index: 623465 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0270. Min Act: -0.0001

Data Index: 769751 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1365913 (Python Code)

Max Activating Token Index: 992