Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4019 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2401. Min Act: -0.0001

Data Index: 374056 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2288. Min Act: -0.0001

Data Index: 458683 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1973. Min Act: -0.0001

Data Index: 671109 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2162. Min Act: -0.0000

Data Index: 472034 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1933. Min Act: -0.0001

Data Index: 942378 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1019199 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1839. Min Act: -0.0001

Data Index: 570109 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1887. Min Act: -0.0001

Data Index: 505536 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1718. Min Act: -0.0001

Data Index: 211247 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1056527 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1638. Min Act: -0.0000

Data Index: 768600 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1558. Min Act: -0.0001

Data Index: 146129 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1468. Min Act: -0.0001

Data Index: 60942 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1261. Min Act: -0.0001

Data Index: 71824 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1364. Min Act: -0.0001

Data Index: 982786 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1514. Min Act: -0.0001

Data Index: 1234742 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1495. Min Act: -0.0000

Data Index: 231387 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1476. Min Act: -0.0001

Data Index: 18266 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1239. Min Act: -0.0001

Data Index: 103485 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1328. Min Act: -0.0001

Data Index: 935165 (C4 (Web Text))

Max Activating Token Index: 168