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

Dataset: The Pile

Neuron 3100 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.8154. Min Act: -0.0000

Data Index: 370117 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1626933 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.6234. Min Act: -0.0000

Data Index: 465268 (The Pile)

Max Activating Token Index: 619

Text #3

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1351588 (The Pile)

Max Activating Token Index: 875

Text #4

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5949. Min Act: -0.0000

Data Index: 337799 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5727. Min Act: -0.0000

Data Index: 838422 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1685773 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1328525 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5147. Min Act: -0.0000

Data Index: 788996 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5783. Min Act: -0.0000

Data Index: 715149 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1372802 (The Pile)

Max Activating Token Index: 970

Text #11

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4868. Min Act: -0.0000

Data Index: 56716 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4962. Min Act: -0.0000

Data Index: 335765 (The Pile)

Max Activating Token Index: 270

Text #13

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4703. Min Act: -0.0000

Data Index: 48867 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4678. Min Act: -0.0000

Data Index: 320059 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1177446 (The Pile)

Max Activating Token Index: 200

Text #16

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1404605 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1394325 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1529211 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1902193 (The Pile)

Max Activating Token Index: 607