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

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

Neuron 947 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: 2.7821. Min Range: -2.7821

Max Act: 2.6844. Min Act: -0.0000

Data Index: 29673 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6341. Min Act: -0.0000

Data Index: 856698 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.7821. Min Act: -0.0000

Data Index: 382319 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.5875. Min Act: -0.0000

Data Index: 320856 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.3678. Min Act: -0.0000

Data Index: 1270774 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.0465. Min Act: -0.0000

Data Index: 493827 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.0011. Min Act: -0.0000

Data Index: 1107897 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.9338. Min Act: -0.0000

Data Index: 406363 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.9045. Min Act: -0.0000

Data Index: 557486 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.9675. Min Act: -0.0000

Data Index: 214867 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.9266. Min Act: -0.0000

Data Index: 54244 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.8918. Min Act: -0.0000

Data Index: 35927 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.7741. Min Act: -0.0000

Data Index: 909481 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.8444. Min Act: -0.0000

Data Index: 778597 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.7195. Min Act: -0.0000

Data Index: 1222334 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.8294. Min Act: -0.0001

Data Index: 1328258 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.8413. Min Act: -0.0000

Data Index: 9493 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.8084. Min Act: -0.0000

Data Index: 259382 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.9098. Min Act: -0.0000

Data Index: 1231990 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 2.7821. Min Range: -2.7821

Max Act: 1.9109. Min Act: -0.0000

Data Index: 743545 (C4 (Web Text))

Max Activating Token Index: 386