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

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

Neuron 3340 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1559. Min Range: -6.1559

Max Act: 6.1559. Min Act: -0.0000

Data Index: 233338 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.9002. Min Act: -0.0000

Data Index: 867143 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.6893. Min Act: -0.0000

Data Index: 1054508 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.4153. Min Act: -0.0000

Data Index: 406076 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.5310. Min Act: -0.0000

Data Index: 445512 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.6286. Min Act: -0.0000

Data Index: 794947 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.1319. Min Act: -0.0000

Data Index: 47024 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.0284. Min Act: -0.0000

Data Index: 332900 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.2815. Min Act: -0.0000

Data Index: 157490 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.0894. Min Act: -0.0000

Data Index: 1302348 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 6.1559. Min Range: -6.1559

Max Act: 2.8836. Min Act: -0.0000

Data Index: 458728 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.1649. Min Act: -0.0000

Data Index: 30641 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 6.1559. Min Range: -6.1559

Max Act: 2.6871. Min Act: -0.0000

Data Index: 791822 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 6.1559. Min Range: -6.1559

Max Act: 2.4013. Min Act: -0.0000

Data Index: 1027608 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.0159. Min Act: -0.0000

Data Index: 1173877 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 6.1559. Min Range: -6.1559

Max Act: 3.0082. Min Act: -0.0000

Data Index: 858921 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 6.1559. Min Range: -6.1559

Max Act: 2.7093. Min Act: -0.0000

Data Index: 1251014 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 6.1559. Min Range: -6.1559

Max Act: 2.6846. Min Act: -0.0000

Data Index: 462946 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 6.1559. Min Range: -6.1559

Max Act: 2.5356. Min Act: -0.0000

Data Index: 556222 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 6.1559. Min Range: -6.1559

Max Act: 2.6663. Min Act: -0.0000

Data Index: 1228992 (C4 (Web Text))

Max Activating Token Index: 651