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

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

Neuron 422 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1862. Min Act: -0.0002

Data Index: 1184349 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1825. Min Act: -0.0002

Data Index: 487961 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1628. Min Act: -0.0002

Data Index: 63497 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1485. Min Act: -0.0003

Data Index: 227704 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1526. Min Act: -0.0003

Data Index: 723501 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1433. Min Act: -0.0003

Data Index: 329175 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1384. Min Act: -0.0003

Data Index: 852196 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1430. Min Act: -0.0003

Data Index: 1220028 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1428. Min Act: -0.0003

Data Index: 969432 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1411. Min Act: -0.0003

Data Index: 1088666 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1335. Min Act: -0.0003

Data Index: 1174286 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1370. Min Act: -0.0002

Data Index: 996199 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1356. Min Act: -0.0003

Data Index: 981750 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1364. Min Act: -0.0002

Data Index: 882325 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1313. Min Act: -0.0003

Data Index: 180223 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1303. Min Act: -0.0002

Data Index: 796693 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1252. Min Act: -0.0003

Data Index: 920087 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1344. Min Act: -0.0003

Data Index: 1268932 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1285. Min Act: -0.0002

Data Index: 35271 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1317. Min Act: -0.0003

Data Index: 70306 (C4 (Web Text))

Max Activating Token Index: 142