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

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

Neuron 4199 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.0360. Min Act: -0.0000

Data Index: 270436 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.0332. Min Act: -0.0000

Data Index: 663239 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.0213. Min Act: -0.0000

Data Index: 481538 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.0282. Min Act: -0.0000

Data Index: 1295338 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.1062. Min Act: -0.0000

Data Index: 1354653 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.9787. Min Act: -0.0000

Data Index: 1056577 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.0792. Min Act: -0.0000

Data Index: 24652 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.0702. Min Act: -0.0000

Data Index: 1108778 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.0565. Min Act: -0.0000

Data Index: 303592 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.1134. Min Act: -0.0000

Data Index: 1190609 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.9283. Min Act: -0.0000

Data Index: 537783 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.9271. Min Act: -0.0000

Data Index: 39279 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.8389. Min Act: -0.0000

Data Index: 1151348 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.1165. Min Act: -0.0000

Data Index: 458511 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.0197. Min Act: -0.0000

Data Index: 692178 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.1407. Min Act: -0.0000

Data Index: 11245 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.0114. Min Act: -0.0000

Data Index: 745477 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.0047. Min Act: -0.0000

Data Index: 738740 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.1233. Min Act: -0.0000

Data Index: 699895 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.1140. Min Act: -0.0000

Data Index: 981800 (C4 (Web Text))

Max Activating Token Index: 169