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

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

Neuron 4661 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.3135. Min Act: -0.0000

Data Index: 525320 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2453. Min Act: -0.0000

Data Index: 828239 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2451. Min Act: -0.0000

Data Index: 55020 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2141. Min Act: -0.0000

Data Index: 729514 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2059. Min Act: -0.0000

Data Index: 636390 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1599. Min Act: -0.0000

Data Index: 785714 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1277447 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1196334 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1318966 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1781. Min Act: -0.0000

Data Index: 997962 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1667. Min Act: -0.0000

Data Index: 746523 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1931. Min Act: -0.0000

Data Index: 495010 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1274225 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1681. Min Act: -0.0000

Data Index: 952855 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1083155 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1271884 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1568. Min Act: -0.0000

Data Index: 132721 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1544751 (Python Code)

Max Activating Token Index: 865

Text #18

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1086039 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1681. Min Act: -0.0000

Data Index: 307925 (C4 (Web Text))

Max Activating Token Index: 705