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

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

Neuron 722 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.3127. Min Act: -0.0000

Data Index: 639276 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.1531. Min Act: -0.0000

Data Index: 496146 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.2062. Min Act: -0.0000

Data Index: 686938 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.1779. Min Act: -0.0000

Data Index: 174058 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.1569. Min Act: -0.0000

Data Index: 1294411 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0817. Min Act: -0.0000

Data Index: 128164 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.1462. Min Act: -0.0000

Data Index: 172039 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0145. Min Act: -0.0000

Data Index: 451047 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9963. Min Act: -0.0000

Data Index: 568270 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0707. Min Act: -0.0000

Data Index: 307197 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1334120 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0528. Min Act: -0.0000

Data Index: 795883 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0071. Min Act: -0.0000

Data Index: 981081 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9310. Min Act: -0.0000

Data Index: 1052567 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9944. Min Act: -0.0000

Data Index: 989254 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1311203 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9781. Min Act: -0.0000

Data Index: 113703 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1177497 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9565. Min Act: -0.0000

Data Index: 259253 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9352. Min Act: -0.0000

Data Index: 98190 (C4 (Web Text))

Max Activating Token Index: 527