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

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

Neuron 2020 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.7217. Min Act: -0.0000

Data Index: 83156 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1293802 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.6308. Min Act: -0.0000

Data Index: 213241 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.6401. Min Act: -0.0000

Data Index: 801246 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5932. Min Act: -0.0000

Data Index: 183396 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.6128. Min Act: -0.0000

Data Index: 938129 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5274. Min Act: -0.0000

Data Index: 562738 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5060. Min Act: -0.0000

Data Index: 493837 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5112. Min Act: -0.0000

Data Index: 681364 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5215. Min Act: -0.0000

Data Index: 81792 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5168. Min Act: -0.0000

Data Index: 831203 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5221. Min Act: -0.0000

Data Index: 796150 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4997. Min Act: -0.0000

Data Index: 750753 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5359. Min Act: -0.0000

Data Index: 676291 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4977. Min Act: -0.0000

Data Index: 992140 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4672. Min Act: -0.0000

Data Index: 864713 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4796. Min Act: -0.0000

Data Index: 611500 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4872. Min Act: -0.0000

Data Index: 13985 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4761. Min Act: -0.0000

Data Index: 542941 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4733. Min Act: -0.0000

Data Index: 735965 (C4 (Web Text))

Max Activating Token Index: 856