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

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

Neuron 614 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.4406. Min Act: -0.0001

Data Index: 1038813 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3433. Min Act: -0.0002

Data Index: 282258 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3711. Min Act: -0.0002

Data Index: 1044391 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.2801. Min Act: -0.0002

Data Index: 738313 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3548. Min Act: -0.0002

Data Index: 356776 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.2356. Min Act: -0.0002

Data Index: 351754 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.2678. Min Act: -0.0002

Data Index: 1339858 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3832. Min Act: -0.0002

Data Index: 27889 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3183. Min Act: -0.0001

Data Index: 1045287 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.1737. Min Act: -0.0002

Data Index: 733577 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.2185. Min Act: -0.0002

Data Index: 397043 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 1.4406. Min Range: -1.4406

Max Act: 0.8891. Min Act: -0.0002

Data Index: 1231103 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 1.4406. Min Range: -1.4406

Max Act: 0.9864. Min Act: -0.0002

Data Index: 1190120 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 1.4406. Min Range: -1.4406

Max Act: 0.9516. Min Act: -0.0002

Data Index: 669901 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.4406. Min Range: -1.4406

Max Act: 0.8898. Min Act: -0.0002

Data Index: 804350 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 1.4406. Min Range: -1.4406

Max Act: 0.9164. Min Act: -0.0001

Data Index: 175302 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 1.4406. Min Range: -1.4406

Max Act: 0.8596. Min Act: -0.0001

Data Index: 51004 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.4406. Min Range: -1.4406

Max Act: 0.8105. Min Act: -0.0001

Data Index: 688899 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 1.4406. Min Range: -1.4406

Max Act: 0.8111. Min Act: -0.0002

Data Index: 1126347 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 1.4406. Min Range: -1.4406

Max Act: 0.7680. Min Act: -0.0002

Data Index: 619568 (C4 (Web Text))

Max Activating Token Index: 251