Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3956 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9263. Min Act: -0.0002

Data Index: 138932 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9257. Min Act: -0.0002

Data Index: 1319187 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9789. Min Act: -0.0002

Data Index: 1012713 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9745. Min Act: -0.0001

Data Index: 255934 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9682. Min Act: -0.0002

Data Index: 63981 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9585. Min Act: -0.0002

Data Index: 1224961 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9281. Min Act: -0.0002

Data Index: 297603 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9523. Min Act: -0.0002

Data Index: 655977 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9149. Min Act: -0.0002

Data Index: 205877 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9318. Min Act: -0.0001

Data Index: 183673 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.8578. Min Act: -0.0002

Data Index: 817544 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.8916. Min Act: -0.0002

Data Index: 808071 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9161. Min Act: -0.0001

Data Index: 91232 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.8773. Min Act: -0.0001

Data Index: 692372 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.8204. Min Act: -0.0001

Data Index: 968361 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9222. Min Act: -0.0001

Data Index: 203454 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9668. Min Act: -0.0001

Data Index: 916704 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9095. Min Act: -0.0001

Data Index: 107561 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9133. Min Act: -0.0001

Data Index: 115081 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.8100. Min Act: -0.0001

Data Index: 799526 (C4 (Web Text))

Max Activating Token Index: 309