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

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

Neuron 1796 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.2126. Min Act: -0.0001

Data Index: 1171365 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1784. Min Act: -0.0001

Data Index: 1041518 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1867. Min Act: -0.0001

Data Index: 563563 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1679. Min Act: -0.0000

Data Index: 843335 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1615. Min Act: -0.0000

Data Index: 345865 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1125287 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1519. Min Act: -0.0001

Data Index: 654383 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1438. Min Act: -0.0001

Data Index: 771940 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1531. Min Act: -0.0000

Data Index: 88230 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1435. Min Act: -0.0001

Data Index: 192007 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1348829 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1405. Min Act: -0.0001

Data Index: 660835 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1471. Min Act: -0.0001

Data Index: 164105 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1416. Min Act: -0.0000

Data Index: 772876 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1418. Min Act: -0.0001

Data Index: 462707 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1470. Min Act: -0.0000

Data Index: 369241 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1408. Min Act: -0.0001

Data Index: 70071 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1230892 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1347. Min Act: -0.0000

Data Index: 135507 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1336. Min Act: -0.0001

Data Index: 922158 (C4 (Web Text))

Max Activating Token Index: 475