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

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

Neuron 3215 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1538153 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2830. Min Act: -0.0000

Data Index: 164534 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1105370 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1185966 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2157. Min Act: -0.0000

Data Index: 295815 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1143662 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1436871 (Python Code)

Max Activating Token Index: 533

Text #7

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2448. Min Act: -0.0000

Data Index: 960364 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2164. Min Act: -0.0000

Data Index: 754149 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2367. Min Act: -0.0000

Data Index: 874075 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2142. Min Act: -0.0000

Data Index: 477930 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1285240 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1475951 (Python Code)

Max Activating Token Index: 971

Text #13

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1044325 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2075. Min Act: -0.0000

Data Index: 550432 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1448189 (Python Code)

Max Activating Token Index: 939

Text #16

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1453812 (Python Code)

Max Activating Token Index: 859

Text #17

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1584073 (Python Code)

Max Activating Token Index: 929

Text #18

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2044. Min Act: -0.0000

Data Index: 825608 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1480788 (Python Code)

Max Activating Token Index: 364