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

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

Neuron 4232 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.9326. Min Act: -0.0002

Data Index: 960563 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8857. Min Act: -0.0002

Data Index: 736179 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8810. Min Act: -0.0002

Data Index: 1300987 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8605. Min Act: -0.0002

Data Index: 1260691 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8477. Min Act: -0.0002

Data Index: 528708 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8281. Min Act: -0.0002

Data Index: 172916 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8281. Min Act: -0.0002

Data Index: 469931 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8429. Min Act: -0.0002

Data Index: 808703 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8301. Min Act: -0.0002

Data Index: 87041 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8270. Min Act: -0.0002

Data Index: 436725 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8130. Min Act: -0.0002

Data Index: 1095199 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8314. Min Act: -0.0003

Data Index: 817275 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8129. Min Act: -0.0002

Data Index: 1142828 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8234. Min Act: -0.0002

Data Index: 223162 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8093. Min Act: -0.0002

Data Index: 86978 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8142. Min Act: -0.0002

Data Index: 273530 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8172. Min Act: -0.0002

Data Index: 702740 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7849. Min Act: -0.0002

Data Index: 798438 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7966. Min Act: -0.0002

Data Index: 174213 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8035. Min Act: -0.0002

Data Index: 275177 (C4 (Web Text))

Max Activating Token Index: 225