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

Dataset: The Pile

Neuron 159 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.6064. Min Act: -0.0000

Data Index: 252810 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.6483. Min Act: 0.0000

Data Index: 94477 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1387051 (The Pile)

Max Activating Token Index: 475

Text #3

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.5482. Min Act: -0.0000

Data Index: 88468 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.5392. Min Act: -0.0000

Data Index: 799184 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1838416 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1514883 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4731. Min Act: -0.0000

Data Index: 410915 (The Pile)

Max Activating Token Index: 724

Text #8

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1844053 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4652. Min Act: -0.0000

Data Index: 959047 (The Pile)

Max Activating Token Index: 141

Text #10

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4465. Min Act: -0.0000

Data Index: 539985 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1835628 (The Pile)

Max Activating Token Index: 895

Text #12

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1276567 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4728. Min Act: -0.0000

Data Index: 543003 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4436. Min Act: -0.0000

Data Index: 506594 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4411. Min Act: -0.0000

Data Index: 954844 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4203. Min Act: 0.0001

Data Index: 883911 (The Pile)

Max Activating Token Index: 853

Text #17

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4172. Min Act: -0.0000

Data Index: 675580 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4021. Min Act: 0.0000

Data Index: 1883969 (The Pile)

Max Activating Token Index: 191

Text #19

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1470789 (The Pile)

Max Activating Token Index: 577