Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 135 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0954. Min Act: -0.0006

Data Index: 1461092 (Python Code)

Max Activating Token Index: 796

Text #1

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0723. Min Act: -0.0006

Data Index: 1624924 (Python Code)

Max Activating Token Index: 539

Text #2

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0595. Min Act: -0.0006

Data Index: 1402882 (Python Code)

Max Activating Token Index: 514

Text #3

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0599. Min Act: -0.0006

Data Index: 1538433 (Python Code)

Max Activating Token Index: 455

Text #4

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0632. Min Act: -0.0006

Data Index: 1406910 (Python Code)

Max Activating Token Index: 998

Text #5

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0612. Min Act: -0.0006

Data Index: 1378810 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0589. Min Act: -0.0006

Data Index: 1504845 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0556. Min Act: -0.0006

Data Index: 1508842 (Python Code)

Max Activating Token Index: 792

Text #8

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0566. Min Act: -0.0006

Data Index: 1458495 (Python Code)

Max Activating Token Index: 786

Text #9

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0588. Min Act: -0.0006

Data Index: 1417208 (Python Code)

Max Activating Token Index: 829

Text #10

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0571. Min Act: -0.0006

Data Index: 1523776 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0584. Min Act: -0.0006

Data Index: 1627179 (Python Code)

Max Activating Token Index: 621

Text #12

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0563. Min Act: -0.0006

Data Index: 1446174 (Python Code)

Max Activating Token Index: 1014

Text #13

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0566. Min Act: -0.0006

Data Index: 1549583 (Python Code)

Max Activating Token Index: 521

Text #14

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0557. Min Act: -0.0006

Data Index: 1538395 (Python Code)

Max Activating Token Index: 789

Text #15

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0558. Min Act: -0.0006

Data Index: 1522299 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0564. Min Act: -0.0006

Data Index: 1478845 (Python Code)

Max Activating Token Index: 1008

Text #17

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0551. Min Act: -0.0006

Data Index: 1575222 (Python Code)

Max Activating Token Index: 631

Text #18

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0554. Min Act: -0.0006

Data Index: 1375087 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0518. Min Act: -0.0006

Data Index: 1379691 (Python Code)

Max Activating Token Index: 167