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

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

Neuron 1071 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: 0.1523. Min Range: -0.1523

Max Act: 0.1523. Min Act: -0.0001

Data Index: 290191 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1414. Min Act: -0.0001

Data Index: 796332 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1482. Min Act: -0.0001

Data Index: 562966 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1412. Min Act: -0.0001

Data Index: 915765 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1372. Min Act: -0.0001

Data Index: 846306 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1372. Min Act: -0.0001

Data Index: 125049 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1171999 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1122759 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1476. Min Act: -0.0001

Data Index: 205559 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1167413 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1308. Min Act: -0.0001

Data Index: 1112603 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1279. Min Act: -0.0001

Data Index: 907203 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1300. Min Act: -0.0001

Data Index: 65643 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1286. Min Act: -0.0001

Data Index: 444496 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1104540 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1236. Min Act: -0.0001

Data Index: 801505 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1179. Min Act: -0.0001

Data Index: 19940 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1144101 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1070810 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1200. Min Act: -0.0001

Data Index: 746187 (C4 (Web Text))

Max Activating Token Index: 940