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

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

Neuron 3878 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1640. Min Act: -0.0002

Data Index: 158106 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1436. Min Act: -0.0001

Data Index: 1017218 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1420. Min Act: -0.0002

Data Index: 518067 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1406. Min Act: -0.0001

Data Index: 716727 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1273. Min Act: -0.0002

Data Index: 939313 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1456. Min Act: -0.0001

Data Index: 44809 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1589702 (Python Code)

Max Activating Token Index: 812

Text #7

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1362. Min Act: -0.0001

Data Index: 18700 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1405. Min Act: -0.0002

Data Index: 769469 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1234598 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1339. Min Act: -0.0002

Data Index: 595649 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1280. Min Act: -0.0002

Data Index: 974581 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1264. Min Act: -0.0001

Data Index: 53199 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1222. Min Act: -0.0001

Data Index: 1240920 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1254. Min Act: -0.0001

Data Index: 257145 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1338. Min Act: -0.0001

Data Index: 766715 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1244. Min Act: -0.0002

Data Index: 441547 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1248. Min Act: -0.0002

Data Index: 672017 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1416898 (Python Code)

Max Activating Token Index: 792

Text #19

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1466770 (Python Code)

Max Activating Token Index: 781