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

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

Neuron 891 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: 0.2482. Min Range: -0.2482

Max Act: 0.2482. Min Act: -0.0001

Data Index: 1002617 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2322. Min Act: -0.0001

Data Index: 962249 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2121. Min Act: -0.0000

Data Index: 359519 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2156. Min Act: -0.0000

Data Index: 460546 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2033. Min Act: -0.0001

Data Index: 733439 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2087. Min Act: -0.0000

Data Index: 637007 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2066. Min Act: -0.0000

Data Index: 114877 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2108. Min Act: -0.0000

Data Index: 80717 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1948. Min Act: -0.0001

Data Index: 1307820 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1211714 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2009. Min Act: -0.0001

Data Index: 858807 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1859. Min Act: -0.0000

Data Index: 653411 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1852. Min Act: -0.0001

Data Index: 1254269 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1832. Min Act: -0.0001

Data Index: 435050 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1888. Min Act: -0.0000

Data Index: 674016 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1887. Min Act: -0.0000

Data Index: 34243 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1927. Min Act: -0.0001

Data Index: 545721 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1732. Min Act: -0.0000

Data Index: 85860 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1908. Min Act: -0.0001

Data Index: 885505 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1964. Min Act: -0.0001

Data Index: 368858 (C4 (Web Text))

Max Activating Token Index: 341