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

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

Neuron 47 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1106. Min Act: -0.0001

Data Index: 45639 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0900. Min Act: -0.0001

Data Index: 241115 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1033279 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0920. Min Act: -0.0001

Data Index: 384645 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0862. Min Act: -0.0001

Data Index: 967263 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1212963 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0849. Min Act: -0.0001

Data Index: 143602 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0819. Min Act: -0.0001

Data Index: 913922 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0775. Min Act: -0.0001

Data Index: 581864 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0833. Min Act: -0.0001

Data Index: 760483 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0833. Min Act: -0.0001

Data Index: 789101 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0829. Min Act: -0.0001

Data Index: 517754 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0824. Min Act: -0.0001

Data Index: 683451 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0793. Min Act: -0.0001

Data Index: 49856 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1332699 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0758. Min Act: -0.0001

Data Index: 198954 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0779. Min Act: -0.0001

Data Index: 1039338 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1040837 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0768. Min Act: -0.0001

Data Index: 645422 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0775. Min Act: -0.0001

Data Index: 346296 (C4 (Web Text))

Max Activating Token Index: 708