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

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

Neuron 2571 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1644. Min Act: -0.0001

Data Index: 409108 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1483. Min Act: -0.0001

Data Index: 203661 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1423. Min Act: -0.0001

Data Index: 866484 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1404. Min Act: -0.0001

Data Index: 431150 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1422. Min Act: -0.0001

Data Index: 298207 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1421. Min Act: -0.0001

Data Index: 1261773 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1420. Min Act: -0.0001

Data Index: 177723 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1393. Min Act: -0.0001

Data Index: 868224 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1446. Min Act: -0.0001

Data Index: 519578 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1394. Min Act: -0.0001

Data Index: 401088 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1371. Min Act: -0.0001

Data Index: 962701 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1352. Min Act: -0.0001

Data Index: 375919 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1302. Min Act: -0.0001

Data Index: 86992 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1346. Min Act: -0.0001

Data Index: 811233 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1252. Min Act: -0.0001

Data Index: 780657 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1150857 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1334. Min Act: -0.0001

Data Index: 778300 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1329. Min Act: -0.0001

Data Index: 313977 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1292. Min Act: -0.0001

Data Index: 1336245 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1324. Min Act: -0.0001

Data Index: 511944 (C4 (Web Text))

Max Activating Token Index: 392