Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6047 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1430085 (Python Code)

Max Activating Token Index: 863

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1559941 (Python Code)

Max Activating Token Index: 587

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1598793 (Python Code)

Max Activating Token Index: 689

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1468270 (Python Code)

Max Activating Token Index: 655

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1511597 (Python Code)

Max Activating Token Index: 789

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1534591 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0246. Min Act: -0.0002

Data Index: 216781 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1425775 (Python Code)

Max Activating Token Index: 1009

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0244. Min Act: -0.0002

Data Index: 494727 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1343166 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1507505 (Python Code)

Max Activating Token Index: 789

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1390266 (Python Code)

Max Activating Token Index: 632

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1590445 (Python Code)

Max Activating Token Index: 323

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0226. Min Act: -0.0002

Data Index: 900948 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1369639 (Python Code)

Max Activating Token Index: 647

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1430372 (Python Code)

Max Activating Token Index: 959

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1524786 (Python Code)

Max Activating Token Index: 761

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1187943 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1522036 (Python Code)

Max Activating Token Index: 232

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1516176 (Python Code)

Max Activating Token Index: 535