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

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

Neuron 1864 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2074. Min Range: -2.2074

Max Act: 2.2074. Min Act: -0.0000

Data Index: 1190066 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.9517. Min Act: -0.0000

Data Index: 358804 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.9394. Min Act: -0.0000

Data Index: 364961 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.9108. Min Act: -0.0000

Data Index: 592244 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.8264. Min Act: -0.0000

Data Index: 535055 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.7630. Min Act: -0.0000

Data Index: 120363 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.7556. Min Act: -0.0000

Data Index: 462465 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.7367. Min Act: -0.0000

Data Index: 787211 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.5736. Min Act: 0.0000

Data Index: 351866 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.5949. Min Act: -0.0000

Data Index: 183862 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.6121. Min Act: -0.0000

Data Index: 843439 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.6451. Min Act: -0.0000

Data Index: 204396 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.5426. Min Act: -0.0000

Data Index: 508187 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.5662. Min Act: -0.0000

Data Index: 679262 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.5183. Min Act: -0.0000

Data Index: 478599 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.4719. Min Act: -0.0000

Data Index: 45674 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.6581. Min Act: -0.0000

Data Index: 1141180 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.5960. Min Act: -0.0000

Data Index: 672943 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.4522. Min Act: -0.0000

Data Index: 253536 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 2.2074. Min Range: -2.2074

Max Act: 1.4968. Min Act: -0.0000

Data Index: 3523 (C4 (Web Text))

Max Activating Token Index: 835