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

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

Neuron 223 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1034840 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.5866. Min Act: -0.0000

Data Index: 216645 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.5810. Min Act: -0.0000

Data Index: 929304 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1202379 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1128836 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.5021. Min Act: -0.0000

Data Index: 974107 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1653756 (Python Code)

Max Activating Token Index: 822

Text #7

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1393197 (Python Code)

Max Activating Token Index: 241

Text #8

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.4575. Min Act: -0.0000

Data Index: 194000 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.4243. Min Act: -0.0000

Data Index: 191413 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.4224. Min Act: -0.0000

Data Index: 1525002 (Python Code)

Max Activating Token Index: 914

Text #11

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1240972 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1548790 (Python Code)

Max Activating Token Index: 967

Text #13

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1347761 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1287459 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.4079. Min Act: -0.0000

Data Index: 403265 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.3867. Min Act: -0.0000

Data Index: 535271 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.3832. Min Act: -0.0000

Data Index: 264382 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1540138 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 0.6291. Min Range: -0.6291

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1435224 (Python Code)

Max Activating Token Index: 715