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

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

Neuron 2428 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: 0.8993. Min Range: -0.8993

Max Act: 0.8993. Min Act: -0.0000

Data Index: 684439 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8775. Min Act: -0.0000

Data Index: 734045 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8499. Min Act: -0.0000

Data Index: 810783 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8692. Min Act: -0.0000

Data Index: 331167 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1211653 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8793. Min Act: -0.0000

Data Index: 608373 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8823. Min Act: -0.0000

Data Index: 768193 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8580. Min Act: -0.0000

Data Index: 10406 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8762. Min Act: -0.0000

Data Index: 22897 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8611. Min Act: -0.0000

Data Index: 507074 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8610. Min Act: -0.0000

Data Index: 400839 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8526. Min Act: -0.0000

Data Index: 786451 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1063531 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8222. Min Act: -0.0000

Data Index: 729553 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8397. Min Act: -0.0000

Data Index: 957003 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8168. Min Act: -0.0000

Data Index: 899746 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8072. Min Act: -0.0000

Data Index: 246880 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8301. Min Act: -0.0000

Data Index: 294011 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.8334. Min Act: -0.0001

Data Index: 420928 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.8993. Min Range: -0.8993

Max Act: 0.7785. Min Act: -0.0000

Data Index: 53242 (C4 (Web Text))

Max Activating Token Index: 917