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

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

Neuron 4686 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: 1.4448. Min Range: -1.4448

Max Act: 1.4448. Min Act: -0.0000

Data Index: 41900 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.4036. Min Act: -0.0000

Data Index: 1284043 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3474. Min Act: 0.0000

Data Index: 1313586 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1340793 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.1574. Min Act: -0.0000

Data Index: 647957 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.1458. Min Act: -0.0000

Data Index: 639692 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.1302. Min Act: -0.0000

Data Index: 703660 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.1187. Min Act: -0.0000

Data Index: 979848 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.1222. Min Act: -0.0000

Data Index: 132511 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.1830. Min Act: -0.0000

Data Index: 435596 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.1722. Min Act: -0.0000

Data Index: 751404 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.0877. Min Act: -0.0000

Data Index: 205633 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1644781 (Python Code)

Max Activating Token Index: 766

Text #13

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1491214 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.0611. Min Act: -0.0000

Data Index: 236771 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.0955. Min Act: -0.0000

Data Index: 301043 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.0879. Min Act: -0.0000

Data Index: 924009 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.0464. Min Act: -0.0000

Data Index: 919733 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.0776. Min Act: -0.0000

Data Index: 968515 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.0364. Min Act: 0.0000

Data Index: 490729 (C4 (Web Text))

Max Activating Token Index: 246