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

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

Neuron 3266 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6005. Min Range: -2.6005

Max Act: 2.6005. Min Act: -0.0001

Data Index: 1649624 (Python Code)

Max Activating Token Index: 772

Text #1

Max Range: 2.6005. Min Range: -2.6005

Max Act: 2.1611. Min Act: -0.0000

Data Index: 1370557 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 2.6005. Min Range: -2.6005

Max Act: 2.1566. Min Act: -0.0000

Data Index: 1562384 (Python Code)

Max Activating Token Index: 431

Text #3

Max Range: 2.6005. Min Range: -2.6005

Max Act: 2.1297. Min Act: -0.0000

Data Index: 19551 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 2.6005. Min Range: -2.6005

Max Act: 2.0350. Min Act: -0.0000

Data Index: 114197 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 2.6005. Min Range: -2.6005

Max Act: 2.0605. Min Act: -0.0000

Data Index: 1645709 (Python Code)

Max Activating Token Index: 969

Text #6

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.7774. Min Act: -0.0000

Data Index: 1370612 (Python Code)

Max Activating Token Index: 391

Text #7

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.9886. Min Act: -0.0000

Data Index: 768142 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.8687. Min Act: -0.0000

Data Index: 789970 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.8509. Min Act: -0.0000

Data Index: 1126779 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.8390. Min Act: -0.0000

Data Index: 1609478 (Python Code)

Max Activating Token Index: 385

Text #11

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.8464. Min Act: -0.0000

Data Index: 1548268 (Python Code)

Max Activating Token Index: 536

Text #12

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.8165. Min Act: -0.0000

Data Index: 746930 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.7075. Min Act: -0.0000

Data Index: 680691 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.6985. Min Act: -0.0001

Data Index: 1369005 (Python Code)

Max Activating Token Index: 568

Text #15

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.7821. Min Act: -0.0000

Data Index: 103125 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.7622. Min Act: -0.0000

Data Index: 780591 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.8816. Min Act: -0.0000

Data Index: 886502 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.5532. Min Act: -0.0000

Data Index: 1623162 (Python Code)

Max Activating Token Index: 682

Text #19

Max Range: 2.6005. Min Range: -2.6005

Max Act: 1.7452. Min Act: -0.0000

Data Index: 744276 (C4 (Web Text))

Max Activating Token Index: 256