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

Dataset: The Pile

Neuron 4416 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: 0.6801. Min Range: -0.6801

Max Act: 0.6801. Min Act: -0.0000

Data Index: 926629 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1919332 (The Pile)

Max Activating Token Index: 798

Text #2

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.6432. Min Act: -0.0000

Data Index: 112928 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5846. Min Act: -0.0000

Data Index: 273103 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1522756 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1496457 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5537. Min Act: -0.0000

Data Index: 410852 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1098032 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1792991 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5770. Min Act: -0.0000

Data Index: 521418 (The Pile)

Max Activating Token Index: 220

Text #10

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5539. Min Act: -0.0000

Data Index: 216221 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1721190 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1538315 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1416313 (The Pile)

Max Activating Token Index: 916

Text #14

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5311. Min Act: -0.0000

Data Index: 682152 (The Pile)

Max Activating Token Index: 221

Text #15

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5313. Min Act: -0.0000

Data Index: 19919 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1631690 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5206. Min Act: -0.0000

Data Index: 850622 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5408. Min Act: -0.0000

Data Index: 772536 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1843334 (The Pile)

Max Activating Token Index: 54