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

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

Neuron 4495 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1076876 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1849. Min Act: -0.0000

Data Index: 240942 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1794. Min Act: -0.0000

Data Index: 169633 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1475. Min Act: -0.0000

Data Index: 140798 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1444. Min Act: -0.0000

Data Index: 336724 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1402. Min Act: -0.0000

Data Index: 744169 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1442. Min Act: -0.0000

Data Index: 843655 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1324. Min Act: -0.0000

Data Index: 858227 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1355. Min Act: -0.0000

Data Index: 687913 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1341. Min Act: -0.0000

Data Index: 48170 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1118056 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1225. Min Act: -0.0000

Data Index: 104920 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1255319 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1303. Min Act: -0.0000

Data Index: 331945 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1289. Min Act: -0.0000

Data Index: 75305 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1208. Min Act: -0.0000

Data Index: 113630 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1285. Min Act: -0.0000

Data Index: 262065 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1212. Min Act: -0.0000

Data Index: 337099 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1197. Min Act: -0.0000

Data Index: 111741 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.2017. Min Range: -0.2017

Max Act: 0.1177. Min Act: -0.0000

Data Index: 225563 (C4 (Web Text))

Max Activating Token Index: 62