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

Dataset: The Pile

Neuron 2667 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: 4.4701. Min Range: -4.4701

Max Act: 4.4701. Min Act: -0.0000

Data Index: 1168531 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 4.4701. Min Range: -4.4701

Max Act: 4.2094. Min Act: -0.0000

Data Index: 1696274 (The Pile)

Max Activating Token Index: 322

Text #2

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.9966. Min Act: -0.0000

Data Index: 1277984 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 4.4701. Min Range: -4.4701

Max Act: 4.2798. Min Act: -0.0000

Data Index: 583250 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.8674. Min Act: -0.0000

Data Index: 158363 (The Pile)

Max Activating Token Index: 627

Text #5

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.7577. Min Act: -0.0000

Data Index: 29631 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.7147. Min Act: -0.0000

Data Index: 778580 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.7991. Min Act: -0.0000

Data Index: 139408 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.5390. Min Act: -0.0000

Data Index: 1122678 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.5654. Min Act: -0.0000

Data Index: 1660082 (The Pile)

Max Activating Token Index: 394

Text #10

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.5161. Min Act: -0.0000

Data Index: 531986 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.5439. Min Act: -0.0000

Data Index: 515404 (The Pile)

Max Activating Token Index: 512

Text #12

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.3571. Min Act: -0.0000

Data Index: 515062 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.5189. Min Act: -0.0000

Data Index: 729903 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.1773. Min Act: -0.0000

Data Index: 845595 (The Pile)

Max Activating Token Index: 307

Text #15

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.5035. Min Act: -0.0000

Data Index: 405805 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.6982. Min Act: -0.0000

Data Index: 772342 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.4581. Min Act: -0.0000

Data Index: 1259881 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.6346. Min Act: -0.0000

Data Index: 1341625 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 4.4701. Min Range: -4.4701

Max Act: 3.7916. Min Act: -0.0000

Data Index: 1066252 (The Pile)

Max Activating Token Index: 560