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

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

Neuron 3509 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2316. Min Act: -0.0000

Data Index: 760098 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1339990 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2065. Min Act: -0.0000

Data Index: 887498 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2033. Min Act: -0.0000

Data Index: 407258 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1196140 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1953. Min Act: -0.0000

Data Index: 650105 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1979. Min Act: -0.0000

Data Index: 39851 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1156605 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1860. Min Act: -0.0000

Data Index: 875488 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1927. Min Act: -0.0000

Data Index: 905227 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1941. Min Act: -0.0000

Data Index: 441838 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1121263 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1230816 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2019. Min Act: -0.0000

Data Index: 524003 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1923. Min Act: -0.0000

Data Index: 236846 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1835. Min Act: -0.0000

Data Index: 908074 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1874. Min Act: -0.0001

Data Index: 57095 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1278979 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1816. Min Act: -0.0001

Data Index: 338375 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1868. Min Act: -0.0000

Data Index: 145754 (C4 (Web Text))

Max Activating Token Index: 547