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

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

Neuron 4988 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1469. Min Act: -0.0002

Data Index: 39167 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1578. Min Act: -0.0002

Data Index: 137840 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1453. Min Act: -0.0002

Data Index: 1065754 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1531. Min Act: -0.0002

Data Index: 261405 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1418. Min Act: -0.0002

Data Index: 548824 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1399. Min Act: -0.0002

Data Index: 981082 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1341. Min Act: -0.0002

Data Index: 159037 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1285. Min Act: -0.0002

Data Index: 444629 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1148557 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1263. Min Act: -0.0002

Data Index: 34193 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1050697 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1436. Min Act: -0.0002

Data Index: 133925 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1314. Min Act: -0.0002

Data Index: 895825 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1340. Min Act: -0.0002

Data Index: 664330 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1342. Min Act: -0.0002

Data Index: 910737 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1421. Min Act: -0.0002

Data Index: 519581 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1372. Min Act: -0.0002

Data Index: 103393 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1321. Min Act: -0.0002

Data Index: 1236653 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1221. Min Act: -0.0002

Data Index: 178026 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1312. Min Act: -0.0002

Data Index: 383467 (C4 (Web Text))

Max Activating Token Index: 47