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

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

Neuron 1096 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.5970. Min Act: 0.0000

Data Index: 1468683 (Python Code)

Max Activating Token Index: 1007

Text #1

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0717. Min Act: -0.0000

Data Index: 70844 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0126. Min Act: -0.0000

Data Index: 803154 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0558. Min Act: -0.0000

Data Index: 58978 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.9626. Min Act: -0.0000

Data Index: 801180 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.8172. Min Act: -0.0000

Data Index: 516041 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.9000. Min Act: -0.0000

Data Index: 844714 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0519. Min Act: -0.0000

Data Index: 496812 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.9530. Min Act: -0.0000

Data Index: 1301499 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.8304. Min Act: -0.0000

Data Index: 810499 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1233642 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.7832. Min Act: -0.0000

Data Index: 565201 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.9616. Min Act: -0.0000

Data Index: 815498 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.8415. Min Act: -0.0000

Data Index: 434545 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1207045 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.8289. Min Act: -0.0000

Data Index: 280294 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.7367. Min Act: -0.0000

Data Index: 541721 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.7803. Min Act: -0.0000

Data Index: 738190 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.8002. Min Act: -0.0000

Data Index: 744871 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 1.5970. Min Range: -1.5970

Max Act: 0.8570. Min Act: -0.0000

Data Index: 604686 (C4 (Web Text))

Max Activating Token Index: 247