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

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

Neuron 1553 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: 1.2623. Min Range: -1.2623

Max Act: 1.2623. Min Act: -0.0001

Data Index: 796968 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.1694. Min Act: -0.0001

Data Index: 1053974 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8542. Min Act: -0.0001

Data Index: 1323427 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8738. Min Act: -0.0001

Data Index: 233597 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8108. Min Act: -0.0001

Data Index: 1266635 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8383. Min Act: -0.0001

Data Index: 1187256 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.6459. Min Act: -0.0001

Data Index: 459222 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8122. Min Act: -0.0001

Data Index: 601670 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8064. Min Act: -0.0001

Data Index: 298388 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8044. Min Act: -0.0001

Data Index: 456880 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7792. Min Act: -0.0001

Data Index: 555201 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7694. Min Act: -0.0001

Data Index: 229162 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8063. Min Act: -0.0001

Data Index: 1349108 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7542. Min Act: -0.0001

Data Index: 374676 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7258. Min Act: -0.0001

Data Index: 414348 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7121. Min Act: -0.0001

Data Index: 728812 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7529. Min Act: -0.0001

Data Index: 166370 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7385. Min Act: -0.0001

Data Index: 1315219 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7293. Min Act: -0.0001

Data Index: 343539 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.6996. Min Act: -0.0001

Data Index: 162390 (C4 (Web Text))

Max Activating Token Index: 222