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

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

Neuron 1554 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.7020. Min Act: -0.0000

Data Index: 248682 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.6833. Min Act: -0.0000

Data Index: 125137 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.6565. Min Act: -0.0000

Data Index: 203274 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.7420. Min Act: -0.0000

Data Index: 312983 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.8224. Min Act: -0.0000

Data Index: 906802 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.7165. Min Act: -0.0000

Data Index: 309921 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.6327. Min Act: -0.0000

Data Index: 658510 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.5516. Min Act: -0.0000

Data Index: 1167490 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.4390. Min Act: -0.0000

Data Index: 295994 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.4933. Min Act: -0.0000

Data Index: 803096 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.4285. Min Act: -0.0000

Data Index: 824812 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.4781. Min Act: -0.0000

Data Index: 67973 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.4778. Min Act: -0.0000

Data Index: 812509 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.3846. Min Act: -0.0000

Data Index: 354976 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.3621. Min Act: -0.0000

Data Index: 711794 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.4326. Min Act: -0.0000

Data Index: 301056 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.5116. Min Act: -0.0000

Data Index: 297862 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.4898. Min Act: -0.0000

Data Index: 1240127 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.2246. Min Act: -0.0000

Data Index: 221555 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 1.8224. Min Range: -1.8224

Max Act: 1.3721. Min Act: -0.0000

Data Index: 736353 (C4 (Web Text))

Max Activating Token Index: 955