Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 300 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1021485 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0610. Min Act: -0.0003

Data Index: 94720 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1283377 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0609. Min Act: -0.0002

Data Index: 164502 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0574. Min Act: -0.0002

Data Index: 21825 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1067570 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0577. Min Act: -0.0003

Data Index: 798519 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0600. Min Act: -0.0003

Data Index: 422242 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0582. Min Act: -0.0003

Data Index: 178215 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0562. Min Act: -0.0003

Data Index: 427064 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0593. Min Act: -0.0003

Data Index: 259950 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0578. Min Act: -0.0003

Data Index: 940045 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0586. Min Act: -0.0002

Data Index: 65379 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0568. Min Act: -0.0003

Data Index: 307803 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0544. Min Act: -0.0003

Data Index: 94701 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0525. Min Act: -0.0002

Data Index: 314847 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0562. Min Act: -0.0003

Data Index: 148703 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1136469 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0559. Min Act: -0.0003

Data Index: 869226 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0564. Min Act: -0.0003

Data Index: 769553 (C4 (Web Text))

Max Activating Token Index: 722