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

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

Neuron 2497 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3865. Min Act: -0.0000

Data Index: 805113 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2944. Min Act: -0.0000

Data Index: 127294 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2551. Min Act: -0.0001

Data Index: 365755 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2725. Min Act: -0.0001

Data Index: 219951 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2419. Min Act: -0.0001

Data Index: 1151869 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2508. Min Act: -0.0000

Data Index: 229103 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1162703 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1289165 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1028202 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2155. Min Act: -0.0001

Data Index: 378620 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2152. Min Act: -0.0000

Data Index: 426841 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1237801 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2106. Min Act: -0.0000

Data Index: 301553 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2038. Min Act: -0.0000

Data Index: 272489 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1994. Min Act: -0.0000

Data Index: 917409 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1981. Min Act: -0.0000

Data Index: 400310 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1918. Min Act: -0.0000

Data Index: 726421 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1891. Min Act: -0.0000

Data Index: 523598 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1961. Min Act: -0.0000

Data Index: 172434 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1880. Min Act: -0.0001

Data Index: 184486 (C4 (Web Text))

Max Activating Token Index: 523