Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1970 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.4546. Min Act: -0.0003

Data Index: 1298893 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.3617. Min Act: -0.0003

Data Index: 1084810 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.2872. Min Act: -0.0003

Data Index: 202585 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.1550. Min Act: -0.0003

Data Index: 1328867 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.2032. Min Act: -0.0003

Data Index: 778062 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.1421. Min Act: -0.0003

Data Index: 963109 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.2699. Min Act: -0.0003

Data Index: 996957 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.9661. Min Act: -0.0003

Data Index: 1267040 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0173. Min Act: -0.0003

Data Index: 835140 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0950. Min Act: -0.0003

Data Index: 858830 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0165. Min Act: -0.0003

Data Index: 763607 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.9059. Min Act: -0.0003

Data Index: 733776 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0095. Min Act: -0.0003

Data Index: 556606 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0554. Min Act: -0.0003

Data Index: 90844 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.9177. Min Act: -0.0003

Data Index: 750873 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.9805. Min Act: -0.0003

Data Index: 691571 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0111. Min Act: -0.0003

Data Index: 635724 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.9126. Min Act: -0.0003

Data Index: 1247714 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 1.4546. Min Range: -1.4546

Max Act: 0.9037. Min Act: -0.0003

Data Index: 1325920 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 1.4546. Min Range: -1.4546

Max Act: 1.0288. Min Act: -0.0003

Data Index: 1044189 (C4 (Web Text))

Max Activating Token Index: 938