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

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

Neuron 3199 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6616. Min Act: -0.0000

Data Index: 631520 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6349. Min Act: -0.0000

Data Index: 447772 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6035. Min Act: -0.0000

Data Index: 902160 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5666. Min Act: 0.0001

Data Index: 513582 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5574. Min Act: -0.0000

Data Index: 369230 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5163. Min Act: -0.0000

Data Index: 471807 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5454. Min Act: -0.0000

Data Index: 800590 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5303. Min Act: -0.0000

Data Index: 663720 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5302. Min Act: -0.0000

Data Index: 679375 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5316. Min Act: 0.0001

Data Index: 733189 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5233. Min Act: 0.0001

Data Index: 1242778 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5043. Min Act: -0.0000

Data Index: 673865 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4851. Min Act: -0.0000

Data Index: 953650 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1147678 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5045. Min Act: -0.0000

Data Index: 998711 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4902. Min Act: -0.0000

Data Index: 313878 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1315987 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4921. Min Act: -0.0000

Data Index: 690442 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4900. Min Act: -0.0000

Data Index: 667263 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1211766 (C4 (Web Text))

Max Activating Token Index: 101