Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2389 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0909. Min Act: -0.0001

Data Index: 742953 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0679. Min Act: -0.0001

Data Index: 388378 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0535. Min Act: -0.0001

Data Index: 712057 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0433. Min Act: -0.0001

Data Index: 730486 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0426. Min Act: -0.0001

Data Index: 125098 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0394. Min Act: -0.0001

Data Index: 933698 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0397. Min Act: -0.0001

Data Index: 843634 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0380. Min Act: -0.0001

Data Index: 964256 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0399. Min Act: -0.0001

Data Index: 529926 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0405. Min Act: -0.0001

Data Index: 553126 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0376. Min Act: -0.0001

Data Index: 127703 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0372. Min Act: -0.0001

Data Index: 125201 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0370. Min Act: -0.0001

Data Index: 38477 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1246795 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1099693 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0344. Min Act: -0.0001

Data Index: 605031 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1342904 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1126150 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1166502 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0339. Min Act: -0.0001

Data Index: 96765 (C4 (Web Text))

Max Activating Token Index: 219