Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1861 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.3292. Min Act: -0.0000

Data Index: 1889022 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1059861 (The Pile)

Max Activating Token Index: 509

Text #2

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1453299 (The Pile)

Max Activating Token Index: 320

Text #3

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1606059 (The Pile)

Max Activating Token Index: 419

Text #4

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1120465 (The Pile)

Max Activating Token Index: 384

Text #5

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.8149. Min Act: -0.0000

Data Index: 144818 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1525943 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.7615. Min Act: -0.0000

Data Index: 391401 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1339569 (The Pile)

Max Activating Token Index: 758

Text #9

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.6830. Min Act: -0.0000

Data Index: 97809 (The Pile)

Max Activating Token Index: 508

Text #10

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1465800 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.7398. Min Act: -0.0000

Data Index: 49468 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.7289. Min Act: -0.0000

Data Index: 888226 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.7759. Min Act: -0.0000

Data Index: 932039 (The Pile)

Max Activating Token Index: 832

Text #14

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1079231 (The Pile)

Max Activating Token Index: 971

Text #15

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1930467 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1369237 (The Pile)

Max Activating Token Index: 561

Text #17

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.6110. Min Act: -0.0000

Data Index: 981253 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1362767 (The Pile)

Max Activating Token Index: 533

Text #19

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.6313. Min Act: -0.0000

Data Index: 124613 (The Pile)

Max Activating Token Index: 614