Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1930 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1284604 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0742. Min Act: -0.0001

Data Index: 568683 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0650. Min Act: -0.0001

Data Index: 878894 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1006654 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0619. Min Act: -0.0001

Data Index: 696881 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0617. Min Act: -0.0001

Data Index: 158401 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0631. Min Act: -0.0001

Data Index: 266162 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0611. Min Act: -0.0001

Data Index: 44483 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0599. Min Act: -0.0001

Data Index: 406962 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0592. Min Act: -0.0001

Data Index: 125487 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0581. Min Act: -0.0001

Data Index: 391581 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1247268 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1206880 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0600. Min Act: -0.0001

Data Index: 74439 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0528. Min Act: -0.0001

Data Index: 602836 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0524. Min Act: -0.0001

Data Index: 732673 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0542. Min Act: -0.0001

Data Index: 253340 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0506. Min Act: -0.0001

Data Index: 327733 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1105157 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0537. Min Act: -0.0001

Data Index: 407590 (C4 (Web Text))

Max Activating Token Index: 608