Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 304 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.2431. Min Act: -0.0000

Data Index: 1026324 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.2835. Min Act: -0.0000

Data Index: 1313641 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.2725. Min Act: -0.0000

Data Index: 569538 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1433. Min Act: -0.0000

Data Index: 1357982 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1595. Min Act: -0.0000

Data Index: 599147 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.2540. Min Act: -0.0000

Data Index: 755971 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1101. Min Act: -0.0000

Data Index: 68137 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.2098. Min Act: -0.0000

Data Index: 352868 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.0927. Min Act: -0.0000

Data Index: 599240 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.0279. Min Act: -0.0000

Data Index: 1126280 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1427. Min Act: -0.0000

Data Index: 281447 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.0086. Min Act: -0.0000

Data Index: 141015 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1120. Min Act: -0.0000

Data Index: 994475 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 2.2835. Min Range: -2.2835

Max Act: 1.8767. Min Act: -0.0000

Data Index: 393795 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 2.2835. Min Range: -2.2835

Max Act: 1.9678. Min Act: -0.0000

Data Index: 825792 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 2.2835. Min Range: -2.2835

Max Act: 1.9436. Min Act: -0.0000

Data Index: 162388 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.0356. Min Act: -0.0000

Data Index: 969050 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 2.2835. Min Range: -2.2835

Max Act: 1.9187. Min Act: -0.0000

Data Index: 1039484 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1349. Min Act: -0.0000

Data Index: 1351264 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 2.2835. Min Range: -2.2835

Max Act: 1.7807. Min Act: -0.0000

Data Index: 473169 (C4 (Web Text))

Max Activating Token Index: 53