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

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

Neuron 1201 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1543424 (Python Code)

Max Activating Token Index: 220

Text #1

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1652452 (Python Code)

Max Activating Token Index: 987

Text #2

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1521152 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1480665 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1374115 (Python Code)

Max Activating Token Index: 457

Text #5

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1502880 (Python Code)

Max Activating Token Index: 498

Text #6

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1429617 (Python Code)

Max Activating Token Index: 694

Text #7

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1533243 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1417233 (Python Code)

Max Activating Token Index: 915

Text #9

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1472697 (Python Code)

Max Activating Token Index: 640

Text #10

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1479601 (Python Code)

Max Activating Token Index: 255

Text #11

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1543565 (Python Code)

Max Activating Token Index: 879

Text #12

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1512512 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1612731 (Python Code)

Max Activating Token Index: 973

Text #14

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3876. Min Act: -0.0000

Data Index: 1638953 (Python Code)

Max Activating Token Index: 907

Text #15

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1623265 (Python Code)

Max Activating Token Index: 737

Text #16

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1646090 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1644656 (Python Code)

Max Activating Token Index: 907

Text #18

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1511723 (Python Code)

Max Activating Token Index: 382

Text #19

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1484901 (Python Code)

Max Activating Token Index: 565