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

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

Neuron 3025 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0002

Data Index: 465835 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1027763 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1111807 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0561. Min Act: -0.0003

Data Index: 352918 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1162313 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0550. Min Act: -0.0002

Data Index: 403225 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0539. Min Act: -0.0002

Data Index: 156422 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0534. Min Act: -0.0002

Data Index: 202233 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0536. Min Act: -0.0002

Data Index: 191624 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0542. Min Act: -0.0002

Data Index: 215023 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0523. Min Act: -0.0002

Data Index: 372530 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1323930 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1050808 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1146529 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0526. Min Act: -0.0002

Data Index: 102074 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1251462 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0517. Min Act: -0.0002

Data Index: 966996 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0518. Min Act: -0.0002

Data Index: 980504 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0511. Min Act: -0.0002

Data Index: 624540 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0530. Min Act: -0.0003

Data Index: 733962 (C4 (Web Text))

Max Activating Token Index: 808