Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3015 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.2089. Min Act: -0.0001

Data Index: 762728 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1534. Min Act: -0.0001

Data Index: 341678 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1434. Min Act: -0.0001

Data Index: 903033 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1481. Min Act: -0.0001

Data Index: 513953 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1482. Min Act: -0.0001

Data Index: 444053 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1375. Min Act: -0.0001

Data Index: 760107 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1378. Min Act: -0.0001

Data Index: 612479 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1348. Min Act: -0.0001

Data Index: 531835 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1324. Min Act: -0.0001

Data Index: 141642 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1342. Min Act: -0.0001

Data Index: 264648 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1250. Min Act: -0.0001

Data Index: 917406 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1260. Min Act: -0.0000

Data Index: 992656 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1251. Min Act: -0.0001

Data Index: 1045097 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1290. Min Act: -0.0001

Data Index: 441925 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1282. Min Act: -0.0001

Data Index: 488333 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1183. Min Act: -0.0001

Data Index: 897747 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1175. Min Act: -0.0001

Data Index: 303 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1233. Min Act: -0.0001

Data Index: 92419 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1201. Min Act: -0.0001

Data Index: 948601 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1193. Min Act: -0.0001

Data Index: 75925 (C4 (Web Text))

Max Activating Token Index: 451