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

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

Neuron 3856 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.2234. Min Act: -0.0000

Data Index: 659436 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.1727. Min Act: -0.0000

Data Index: 497740 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1109075 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.0120. Min Act: -0.0001

Data Index: 10477 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9832. Min Act: -0.0000

Data Index: 270102 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9442. Min Act: -0.0000

Data Index: 849288 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1196121 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9498. Min Act: -0.0000

Data Index: 637725 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8784. Min Act: -0.0000

Data Index: 410182 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9319. Min Act: -0.0000

Data Index: 575304 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9466. Min Act: -0.0000

Data Index: 378177 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8322. Min Act: -0.0001

Data Index: 869458 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9141. Min Act: -0.0001

Data Index: 1247571 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8996. Min Act: -0.0001

Data Index: 974609 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1315465 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1031402 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1311698 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8780. Min Act: -0.0000

Data Index: 956760 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8764. Min Act: -0.0000

Data Index: 971438 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8553. Min Act: -0.0000

Data Index: 802996 (C4 (Web Text))

Max Activating Token Index: 990