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

Dataset: The Pile

Neuron 404 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1825022 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1541914 (The Pile)

Max Activating Token Index: 838

Text #2

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1499360 (The Pile)

Max Activating Token Index: 450

Text #3

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1419401 (The Pile)

Max Activating Token Index: 920

Text #4

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1968944 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1861584 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5474. Min Act: -0.0000

Data Index: 991025 (The Pile)

Max Activating Token Index: 817

Text #7

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5957. Min Act: -0.0000

Data Index: 320167 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1575794 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6181. Min Act: -0.0000

Data Index: 958221 (The Pile)

Max Activating Token Index: 704

Text #10

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5652. Min Act: -0.0000

Data Index: 315722 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1299412 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1264591 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1304162 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5577. Min Act: -0.0000

Data Index: 636388 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1044928 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1419836 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1342432 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1108821 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1735259 (The Pile)

Max Activating Token Index: 989