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

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

Neuron 845 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.8257. Min Act: -0.0001

Data Index: 1200679 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.8100. Min Act: -0.0001

Data Index: 1075277 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.8237. Min Act: -0.0001

Data Index: 936080 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.7691. Min Act: -0.0001

Data Index: 1343889 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.7373. Min Act: -0.0001

Data Index: 484854 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.7005. Min Act: -0.0001

Data Index: 154414 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.6882. Min Act: -0.0001

Data Index: 938670 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.6406. Min Act: -0.0001

Data Index: 481810 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.6223. Min Act: -0.0001

Data Index: 1204521 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.6411. Min Act: -0.0001

Data Index: 618545 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.6250. Min Act: -0.0001

Data Index: 922483 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.5817. Min Act: -0.0001

Data Index: 242628 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.6092. Min Act: -0.0001

Data Index: 800671 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.6145. Min Act: -0.0001

Data Index: 523981 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.6511. Min Act: -0.0001

Data Index: 1170753 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.6399. Min Act: -0.0001

Data Index: 637942 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.5868. Min Act: -0.0001

Data Index: 1294871 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.6347. Min Act: -0.0001

Data Index: 398919 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.5945. Min Act: -0.0001

Data Index: 859980 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.8257. Min Range: -0.8257

Max Act: 0.6103. Min Act: -0.0001

Data Index: 104375 (C4 (Web Text))

Max Activating Token Index: 494