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

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

Neuron 1894 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: 0.6619. Min Range: -0.6619

Max Act: 0.6442. Min Act: -0.0000

Data Index: 48393 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.6619. Min Act: -0.0000

Data Index: 782731 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5951. Min Act: -0.0000

Data Index: 406772 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5466. Min Act: -0.0001

Data Index: 1262072 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5636. Min Act: -0.0000

Data Index: 907142 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5280. Min Act: -0.0001

Data Index: 167150 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5272. Min Act: -0.0000

Data Index: 453204 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.6413. Min Act: -0.0001

Data Index: 155798 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5083. Min Act: -0.0000

Data Index: 349913 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.4926. Min Act: -0.0000

Data Index: 215327 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1054925 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5033. Min Act: -0.0000

Data Index: 690637 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1261319 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.4802. Min Act: -0.0000

Data Index: 808788 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.4757. Min Act: -0.0000

Data Index: 460291 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5017. Min Act: -0.0000

Data Index: 615023 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.4884. Min Act: -0.0000

Data Index: 134500 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.4703. Min Act: -0.0001

Data Index: 882858 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.4669. Min Act: -0.0000

Data Index: 262201 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.4429. Min Act: -0.0000

Data Index: 116942 (C4 (Web Text))

Max Activating Token Index: 717