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

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

Neuron 660 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1204394 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1454. Min Act: -0.0000

Data Index: 203459 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1608. Min Act: -0.0000

Data Index: 103409 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1468. Min Act: -0.0001

Data Index: 491160 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1301225 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1207. Min Act: -0.0000

Data Index: 813252 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1203. Min Act: -0.0001

Data Index: 209916 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1152. Min Act: -0.0000

Data Index: 147294 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1241. Min Act: -0.0000

Data Index: 497799 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1180. Min Act: -0.0000

Data Index: 230962 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1242. Min Act: -0.0001

Data Index: 957234 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1121. Min Act: -0.0000

Data Index: 595965 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1074825 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1109. Min Act: -0.0000

Data Index: 297472 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1363. Min Act: -0.0000

Data Index: 334183 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1222. Min Act: -0.0001

Data Index: 970036 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1021625 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1244. Min Act: -0.0000

Data Index: 305495 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1145. Min Act: -0.0000

Data Index: 687133 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1058. Min Act: -0.0000

Data Index: 132902 (C4 (Web Text))

Max Activating Token Index: 694