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

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

Neuron 451 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0370. Min Range: -1.0370

Max Act: 1.0370. Min Act: -0.0001

Data Index: 1330055 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.9983. Min Act: -0.0002

Data Index: 12035 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 1.0370. Min Range: -1.0370

Max Act: 1.0284. Min Act: -0.0001

Data Index: 700016 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.9949. Min Act: -0.0002

Data Index: 373014 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.9053. Min Act: -0.0002

Data Index: 62751 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.8989. Min Act: -0.0001

Data Index: 1454806 (Python Code)

Max Activating Token Index: 921

Text #6

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.8465. Min Act: -0.0001

Data Index: 699174 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.9201. Min Act: -0.0001

Data Index: 1136932 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.9434. Min Act: -0.0001

Data Index: 67456 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.8460. Min Act: -0.0001

Data Index: 606247 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.8959. Min Act: -0.0002

Data Index: 1156729 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.8839. Min Act: -0.0001

Data Index: 599018 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.7801. Min Act: -0.0001

Data Index: 370353 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.9092. Min Act: -0.0002

Data Index: 381311 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.9555. Min Act: -0.0001

Data Index: 507066 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.8930. Min Act: -0.0001

Data Index: 741348 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.9189. Min Act: -0.0001

Data Index: 699617 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.8247. Min Act: -0.0001

Data Index: 906362 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.8469. Min Act: -0.0002

Data Index: 836799 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.8198. Min Act: -0.0002

Data Index: 419568 (C4 (Web Text))

Max Activating Token Index: 465