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

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

Neuron 902 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1618. Min Act: -0.0000

Data Index: 166037 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1513. Min Act: -0.0000

Data Index: 582958 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1454. Min Act: -0.0001

Data Index: 1401597 (Python Code)

Max Activating Token Index: 527

Text #3

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1514878 (Python Code)

Max Activating Token Index: 939

Text #4

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1411. Min Act: 0.0000

Data Index: 1552270 (Python Code)

Max Activating Token Index: 687

Text #5

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1439431 (Python Code)

Max Activating Token Index: 62

Text #6

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1446955 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1313. Min Act: 0.0000

Data Index: 1454730 (Python Code)

Max Activating Token Index: 916

Text #8

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1433595 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1255. Min Act: 0.0000

Data Index: 1295003 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1551008 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1401861 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1587473 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1466909 (Python Code)

Max Activating Token Index: 295

Text #14

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1388147 (Python Code)

Max Activating Token Index: 324

Text #15

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1177. Min Act: -0.0000

Data Index: 370486 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1642247 (Python Code)

Max Activating Token Index: 445

Text #17

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1384996 (Python Code)

Max Activating Token Index: 742

Text #18

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1397799 (Python Code)

Max Activating Token Index: 147

Text #19

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1204. Min Act: 0.0000

Data Index: 1425208 (Python Code)

Max Activating Token Index: 153