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

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

Neuron 2576 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: 0.1745. Min Range: -0.1745

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1178955 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1338814 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1613. Min Act: -0.0001

Data Index: 399186 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1437. Min Act: -0.0001

Data Index: 513515 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1411. Min Act: -0.0001

Data Index: 66670 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1500. Min Act: -0.0001

Data Index: 267892 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1080060 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1153994 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1456. Min Act: -0.0001

Data Index: 905546 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1379. Min Act: -0.0001

Data Index: 452655 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1274. Min Act: -0.0001

Data Index: 489863 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1500139 (Python Code)

Max Activating Token Index: 851

Text #12

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1318. Min Act: -0.0001

Data Index: 116425 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1405. Min Act: -0.0001

Data Index: 247 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1516977 (Python Code)

Max Activating Token Index: 439

Text #15

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1602670 (Python Code)

Max Activating Token Index: 328

Text #16

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1032475 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1175629 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1134675 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1363998 (Python Code)

Max Activating Token Index: 124