Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0966. Min Act: -0.0000

Data Index: 71891 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0740. Min Act: -0.0000

Data Index: 229474 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1098990 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0672. Min Act: -0.0000

Data Index: 932158 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0664. Min Act: -0.0000

Data Index: 1242647 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1200450 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0610. Min Act: -0.0000

Data Index: 162471 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1098909 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0589. Min Act: -0.0000

Data Index: 340409 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0566. Min Act: -0.0000

Data Index: 22820 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1130737 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0517. Min Act: -0.0000

Data Index: 671988 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1113177 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0491. Min Act: -0.0000

Data Index: 1342295 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1349302 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0505. Min Act: -0.0000

Data Index: 45548 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1233932 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0522. Min Act: -0.0000

Data Index: 337240 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0530. Min Act: -0.0000

Data Index: 358845 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1174395 (C4 (Web Text))

Max Activating Token Index: 938