Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4452 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1059. Min Range: -2.1059

Max Act: 2.0903. Min Act: -0.0001

Data Index: 1494374 (Python Code)

Max Activating Token Index: 634

Text #1

Max Range: 2.1059. Min Range: -2.1059

Max Act: 2.1059. Min Act: -0.0000

Data Index: 1625528 (Python Code)

Max Activating Token Index: 809

Text #2

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.9402. Min Act: -0.0001

Data Index: 1592950 (Python Code)

Max Activating Token Index: 756

Text #3

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.9134. Min Act: -0.0000

Data Index: 1375191 (Python Code)

Max Activating Token Index: 503

Text #4

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.8692. Min Act: -0.0001

Data Index: 1447179 (Python Code)

Max Activating Token Index: 794

Text #5

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.8158. Min Act: -0.0001

Data Index: 1536269 (Python Code)

Max Activating Token Index: 598

Text #6

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.8450. Min Act: -0.0001

Data Index: 1473320 (Python Code)

Max Activating Token Index: 540

Text #7

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1583068 (Python Code)

Max Activating Token Index: 55

Text #8

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.8101. Min Act: -0.0001

Data Index: 1449479 (Python Code)

Max Activating Token Index: 185

Text #9

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.7756. Min Act: -0.0000

Data Index: 1470694 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.8241. Min Act: -0.0001

Data Index: 1545167 (Python Code)

Max Activating Token Index: 493

Text #11

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.8089. Min Act: -0.0000

Data Index: 1486596 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.6757. Min Act: -0.0000

Data Index: 1407281 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.7881. Min Act: -0.0000

Data Index: 1491263 (Python Code)

Max Activating Token Index: 463

Text #14

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.7280. Min Act: -0.0000

Data Index: 1468743 (Python Code)

Max Activating Token Index: 900

Text #15

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.6955. Min Act: -0.0000

Data Index: 1462964 (Python Code)

Max Activating Token Index: 704

Text #16

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.7162. Min Act: -0.0001

Data Index: 1442107 (Python Code)

Max Activating Token Index: 497

Text #17

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.8262. Min Act: -0.0000

Data Index: 1466452 (Python Code)

Max Activating Token Index: 985

Text #18

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.8159. Min Act: -0.0001

Data Index: 1598904 (Python Code)

Max Activating Token Index: 494

Text #19

Max Range: 2.1059. Min Range: -2.1059

Max Act: 1.7270. Min Act: -0.0000

Data Index: 1507734 (Python Code)

Max Activating Token Index: 475