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

Dataset: The Pile

Neuron 1158 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1303. Min Range: -4.1303

Max Act: 4.1303. Min Act: -0.0000

Data Index: 1209914 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.8058. Min Act: -0.0000

Data Index: 37160 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.3622. Min Act: -0.0000

Data Index: 173575 (The Pile)

Max Activating Token Index: 562

Text #3

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.6381. Min Act: -0.0000

Data Index: 1654742 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.6406. Min Act: -0.0000

Data Index: 1822612 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.3996. Min Act: -0.0000

Data Index: 1225563 (The Pile)

Max Activating Token Index: 988

Text #6

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.3036. Min Act: -0.0000

Data Index: 707914 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.1494. Min Act: -0.0000

Data Index: 1096280 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.2838. Min Act: -0.0000

Data Index: 1029057 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.2541. Min Act: -0.0000

Data Index: 556758 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.2592. Min Act: -0.0000

Data Index: 1129225 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.0862. Min Act: -0.0000

Data Index: 1047338 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.3003. Min Act: -0.0000

Data Index: 1960335 (The Pile)

Max Activating Token Index: 47

Text #13

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.1338. Min Act: -0.0000

Data Index: 959343 (The Pile)

Max Activating Token Index: 12

Text #14

Max Range: 4.1303. Min Range: -4.1303

Max Act: 2.9368. Min Act: -0.0000

Data Index: 1828366 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 4.1303. Min Range: -4.1303

Max Act: 2.9480. Min Act: -0.0000

Data Index: 1321780 (The Pile)

Max Activating Token Index: 455

Text #16

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.0657. Min Act: -0.0000

Data Index: 1407876 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.1568. Min Act: -0.0000

Data Index: 1953037 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 4.1303. Min Range: -4.1303

Max Act: 2.9884. Min Act: -0.0000

Data Index: 498639 (The Pile)

Max Activating Token Index: 578

Text #19

Max Range: 4.1303. Min Range: -4.1303

Max Act: 2.9923. Min Act: -0.0000

Data Index: 1297498 (The Pile)

Max Activating Token Index: 785