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

Dataset: The Pile

Neuron 2883 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: 4.1846. Min Range: -4.1846

Max Act: 4.1846. Min Act: -0.0000

Data Index: 698135 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 4.1846. Min Range: -4.1846

Max Act: 3.0191. Min Act: -0.0000

Data Index: 1350738 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 4.1846. Min Range: -4.1846

Max Act: 3.4181. Min Act: -0.0000

Data Index: 1276398 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 4.1846. Min Range: -4.1846

Max Act: 3.0970. Min Act: -0.0000

Data Index: 1232167 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 4.1846. Min Range: -4.1846

Max Act: 2.8872. Min Act: -0.0000

Data Index: 1491914 (The Pile)

Max Activating Token Index: 867

Text #5

Max Range: 4.1846. Min Range: -4.1846

Max Act: 2.2350. Min Act: -0.0000

Data Index: 941630 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 4.1846. Min Range: -4.1846

Max Act: 2.4852. Min Act: -0.0000

Data Index: 268031 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 4.1846. Min Range: -4.1846

Max Act: 2.2044. Min Act: -0.0000

Data Index: 335318 (The Pile)

Max Activating Token Index: 485

Text #8

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.8575. Min Act: -0.0000

Data Index: 164025 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.5446. Min Act: -0.0000

Data Index: 1239001 (The Pile)

Max Activating Token Index: 856

Text #10

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.6371. Min Act: -0.0000

Data Index: 87709 (The Pile)

Max Activating Token Index: 554

Text #11

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.6035. Min Act: -0.0000

Data Index: 716039 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.5687. Min Act: -0.0000

Data Index: 1203318 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1432170 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.4415. Min Act: -0.0000

Data Index: 919399 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.3823. Min Act: -0.0000

Data Index: 891997 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1642323 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.3946. Min Act: -0.0000

Data Index: 1459753 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.4966. Min Act: -0.0000

Data Index: 1662207 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 4.1846. Min Range: -4.1846

Max Act: 1.4735. Min Act: -0.0000

Data Index: 1920875 (The Pile)

Max Activating Token Index: 485