Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 88 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1664. Min Act: -0.0002

Data Index: 307268 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1608. Min Act: -0.0001

Data Index: 55614 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1515. Min Act: -0.0001

Data Index: 470262 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1513. Min Act: -0.0001

Data Index: 594927 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1141160 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1386. Min Act: -0.0001

Data Index: 809160 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1449. Min Act: -0.0001

Data Index: 467855 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1356. Min Act: -0.0001

Data Index: 897488 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1267. Min Act: -0.0001

Data Index: 726104 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1184431 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1001964 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1388. Min Act: -0.0002

Data Index: 201487 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1016097 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1386. Min Act: -0.0001

Data Index: 803590 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1231413 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1071651 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1171. Min Act: -0.0001

Data Index: 402139 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1216. Min Act: -0.0002

Data Index: 200316 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1114. Min Act: -0.0001

Data Index: 809563 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1161. Min Act: -0.0001

Data Index: 133557 (C4 (Web Text))

Max Activating Token Index: 119