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

Dataset: The Pile

Neuron 3198 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: 3.2739. Min Range: -3.2739

Max Act: 3.2739. Min Act: -0.0000

Data Index: 1093770 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.9002. Min Act: -0.0000

Data Index: 796573 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.6564. Min Act: -0.0000

Data Index: 526518 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.6490. Min Act: -0.0000

Data Index: 138447 (The Pile)

Max Activating Token Index: 453

Text #4

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.8173. Min Act: -0.0000

Data Index: 480927 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.6804. Min Act: -0.0000

Data Index: 723991 (The Pile)

Max Activating Token Index: 20

Text #6

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.3139. Min Act: -0.0000

Data Index: 596400 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1597487 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.5854. Min Act: -0.0000

Data Index: 1096801 (The Pile)

Max Activating Token Index: 449

Text #9

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.3823. Min Act: -0.0000

Data Index: 1320056 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.4202. Min Act: -0.0000

Data Index: 181780 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.3582. Min Act: -0.0000

Data Index: 503945 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.2444. Min Act: -0.0000

Data Index: 864379 (The Pile)

Max Activating Token Index: 836

Text #13

Max Range: 3.2739. Min Range: -3.2739

Max Act: 1.8866. Min Act: -0.0000

Data Index: 506934 (The Pile)

Max Activating Token Index: 792

Text #14

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.0073. Min Act: -0.0000

Data Index: 1335686 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.2687. Min Act: -0.0000

Data Index: 744038 (The Pile)

Max Activating Token Index: 624

Text #16

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.0967. Min Act: -0.0000

Data Index: 590177 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.0856. Min Act: -0.0000

Data Index: 1567979 (The Pile)

Max Activating Token Index: 105

Text #18

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.1712. Min Act: -0.0000

Data Index: 1966954 (The Pile)

Max Activating Token Index: 839

Text #19

Max Range: 3.2739. Min Range: -3.2739

Max Act: 2.0317. Min Act: -0.0000

Data Index: 1163388 (The Pile)

Max Activating Token Index: 796