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

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

Neuron 1987 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.4470. Min Act: -0.0001

Data Index: 626294 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.2705. Min Act: -0.0000

Data Index: 828789 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.1241. Min Act: -0.0000

Data Index: 771414 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.0774. Min Act: -0.0001

Data Index: 460187 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.0415. Min Act: -0.0001

Data Index: 145212 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1019652 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.0247. Min Act: -0.0001

Data Index: 861578 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.0714. Min Act: -0.0001

Data Index: 1252678 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.0086. Min Act: -0.0001

Data Index: 469018 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.0244. Min Act: -0.0001

Data Index: 35933 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 1.4470. Min Range: -1.4470

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1279494 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.0107. Min Act: -0.0001

Data Index: 244809 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 1.4470. Min Range: -1.4470

Max Act: 0.9789. Min Act: -0.0001

Data Index: 140727 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 1.4470. Min Range: -1.4470

Max Act: 0.9434. Min Act: -0.0000

Data Index: 819479 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.4470. Min Range: -1.4470

Max Act: 0.9621. Min Act: -0.0001

Data Index: 434465 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 1.4470. Min Range: -1.4470

Max Act: 0.9642. Min Act: -0.0001

Data Index: 1183631 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 1.4470. Min Range: -1.4470

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1129274 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.0556. Min Act: -0.0000

Data Index: 1267393 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.0058. Min Act: -0.0001

Data Index: 252079 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.4470. Min Range: -1.4470

Max Act: 1.0017. Min Act: -0.0001

Data Index: 1035060 (C4 (Web Text))

Max Activating Token Index: 440