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

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

Neuron 667 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.9900. Min Act: -0.0000

Data Index: 49730 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.7646. Min Act: -0.0000

Data Index: 28560 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.6911. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.7727. Min Act: -0.0000

Data Index: 677519 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.4512. Min Act: -0.0000

Data Index: 1551559 (Python Code)

Max Activating Token Index: 916

Text #5

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.6275. Min Act: -0.0000

Data Index: 1448445 (Python Code)

Max Activating Token Index: 905

Text #6

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.5674. Min Act: -0.0000

Data Index: 1423419 (Python Code)

Max Activating Token Index: 280

Text #7

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.4514. Min Act: -0.0000

Data Index: 1044811 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.5729. Min Act: -0.0000

Data Index: 1225734 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.4767. Min Act: -0.0000

Data Index: 1063091 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1405910 (Python Code)

Max Activating Token Index: 988

Text #11

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.3812. Min Act: -0.0000

Data Index: 467341 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.4426. Min Act: -0.0000

Data Index: 342096 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.4417. Min Act: -0.0000

Data Index: 1040039 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.4415. Min Act: -0.0000

Data Index: 301963 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.3583. Min Act: -0.0000

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.4192. Min Act: -0.0000

Data Index: 100114 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.3354. Min Act: -0.0000

Data Index: 765123 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.3907. Min Act: -0.0000

Data Index: 1035667 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 1.9900. Min Range: -1.9900

Max Act: 1.3351. Min Act: -0.0000

Data Index: 538386 (C4 (Web Text))

Max Activating Token Index: 195