Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2578 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.3144. Min Act: -0.0001

Data Index: 1093647 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.2548. Min Act: -0.0001

Data Index: 961977 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.2555. Min Act: -0.0001

Data Index: 119286 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.2114. Min Act: -0.0001

Data Index: 567458 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.2229. Min Act: -0.0001

Data Index: 83623 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.1793. Min Act: -0.0001

Data Index: 811762 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.1759. Min Act: -0.0001

Data Index: 1095924 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.1103. Min Act: -0.0001

Data Index: 328019 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.0651. Min Act: -0.0001

Data Index: 325810 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.1244. Min Act: -0.0001

Data Index: 571936 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.1952. Min Act: -0.0001

Data Index: 23382 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.1332. Min Act: -0.0001

Data Index: 1128504 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.1777. Min Act: -0.0001

Data Index: 632930 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.0731. Min Act: -0.0001

Data Index: 543825 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.2010. Min Act: -0.0001

Data Index: 229930 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.0652. Min Act: -0.0001

Data Index: 1277221 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.1617. Min Act: -0.0001

Data Index: 172203 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.1738. Min Act: -0.0001

Data Index: 491401 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.3144. Min Range: -1.3144

Max Act: 1.1066. Min Act: -0.0001

Data Index: 673954 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 1.3144. Min Range: -1.3144

Max Act: 0.9883. Min Act: -0.0001

Data Index: 514398 (C4 (Web Text))

Max Activating Token Index: 586