Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 264 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1646. Min Act: 0.0000

Data Index: 1032324 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1040534 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1598. Min Act: 0.0004

Data Index: 490891 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1471. Min Act: 0.0000

Data Index: 549130 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1465. Min Act: 0.0000

Data Index: 721431 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1465. Min Act: 0.0005

Data Index: 406512 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1344. Min Act: 0.0001

Data Index: 742110 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1363. Min Act: 0.0001

Data Index: 814009 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1430. Min Act: -0.0002

Data Index: 1101756 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1368. Min Act: 0.0000

Data Index: 1222914 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1383. Min Act: -0.0002

Data Index: 1029083 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1334. Min Act: -0.0001

Data Index: 89868 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1063714 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1316. Min Act: 0.0005

Data Index: 374715 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1359267 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1270. Min Act: -0.0002

Data Index: 613098 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1279. Min Act: -0.0002

Data Index: 943069 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1269. Min Act: -0.0001

Data Index: 859612 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1146014 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1255. Min Act: 0.0001

Data Index: 6425 (C4 (Web Text))

Max Activating Token Index: 336