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

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

Neuron 612 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5138. Min Act: -0.0002

Data Index: 1609097 (Python Code)

Max Activating Token Index: 134

Text #1

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5349. Min Act: -0.0002

Data Index: 1641276 (Python Code)

Max Activating Token Index: 522

Text #2

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5119. Min Act: -0.0002

Data Index: 1556973 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.3834. Min Act: -0.0002

Data Index: 1411296 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.3745. Min Act: -0.0002

Data Index: 1501276 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.4302. Min Act: -0.0002

Data Index: 1397121 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.3801. Min Act: -0.0002

Data Index: 1477606 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2541. Min Act: -0.0002

Data Index: 1418976 (Python Code)

Max Activating Token Index: 925

Text #8

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.3092. Min Act: -0.0002

Data Index: 1404592 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.3732. Min Act: -0.0002

Data Index: 1410712 (Python Code)

Max Activating Token Index: 755

Text #10

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5675. Min Act: -0.0002

Data Index: 1373671 (Python Code)

Max Activating Token Index: 1019

Text #11

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2337. Min Act: -0.0002

Data Index: 1520834 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1160. Min Act: -0.0002

Data Index: 1370255 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.0042. Min Act: -0.0002

Data Index: 1390278 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1977. Min Act: -0.0002

Data Index: 1647028 (Python Code)

Max Activating Token Index: 296

Text #15

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1587. Min Act: -0.0002

Data Index: 1547942 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1277. Min Act: -0.0002

Data Index: 1567409 (Python Code)

Max Activating Token Index: 1012

Text #17

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.0521. Min Act: -0.0002

Data Index: 1385095 (Python Code)

Max Activating Token Index: 161

Text #18

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1384. Min Act: -0.0002

Data Index: 1602633 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2133. Min Act: -0.0002

Data Index: 1498796 (Python Code)

Max Activating Token Index: 891