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

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

Neuron 1056 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: 0.1545. Min Range: -0.1545

Max Act: 0.1465. Min Act: -0.0002

Data Index: 552210 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1545. Min Act: -0.0002

Data Index: 222072 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1359. Min Act: -0.0002

Data Index: 385695 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1128. Min Act: -0.0002

Data Index: 571833 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1055630 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1335. Min Act: -0.0002

Data Index: 888237 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1259. Min Act: -0.0002

Data Index: 404221 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1213. Min Act: -0.0002

Data Index: 664529 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1202. Min Act: -0.0002

Data Index: 157289 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1242. Min Act: -0.0002

Data Index: 262625 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1099. Min Act: -0.0002

Data Index: 874251 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1216. Min Act: -0.0002

Data Index: 484840 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1117. Min Act: -0.0002

Data Index: 129036 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1074570 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1072. Min Act: -0.0002

Data Index: 54892 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1130. Min Act: -0.0002

Data Index: 261173 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0754. Min Act: -0.0002

Data Index: 385436 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0954. Min Act: -0.0002

Data Index: 987085 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1024. Min Act: -0.0002

Data Index: 963838 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0944. Min Act: -0.0002

Data Index: 509048 (C4 (Web Text))

Max Activating Token Index: 779