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

Dataset: The Pile

Neuron 956 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: 0.4328. Min Range: -0.4328

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1940698 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1360137 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1191219 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1545631 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1751612 (The Pile)

Max Activating Token Index: 689

Text #5

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1478768 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1288532 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1575753 (The Pile)

Max Activating Token Index: 918

Text #8

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3573. Min Act: -0.0000

Data Index: 866917 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3622. Min Act: -0.0000

Data Index: 269190 (The Pile)

Max Activating Token Index: 781

Text #10

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3163. Min Act: -0.0000

Data Index: 621170 (The Pile)

Max Activating Token Index: 764

Text #11

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3142. Min Act: -0.0000

Data Index: 360008 (The Pile)

Max Activating Token Index: 1018

Text #12

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1246412 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1065460 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3371. Min Act: -0.0000

Data Index: 193066 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3055. Min Act: -0.0000

Data Index: 782119 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3273. Min Act: -0.0000

Data Index: 515225 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3113. Min Act: -0.0000

Data Index: 279829 (The Pile)

Max Activating Token Index: 494

Text #18

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1493870 (The Pile)

Max Activating Token Index: 640

Text #19

Max Range: 0.4328. Min Range: -0.4328

Max Act: 0.3270. Min Act: -0.0000

Data Index: 90851 (The Pile)

Max Activating Token Index: 820