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

Dataset: The Pile

Neuron 3634 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9959. Min Act: -0.0000

Data Index: 822775 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 1.0280. Min Range: -1.0280

Max Act: 1.0280. Min Act: -0.0000

Data Index: 598783 (The Pile)

Max Activating Token Index: 576

Text #2

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9920. Min Act: -0.0000

Data Index: 93618 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9141. Min Act: -0.0000

Data Index: 979575 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1658491 (The Pile)

Max Activating Token Index: 888

Text #5

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1327186 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1751719 (The Pile)

Max Activating Token Index: 952

Text #7

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9205. Min Act: -0.0000

Data Index: 61195 (The Pile)

Max Activating Token Index: 440

Text #8

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1072023 (The Pile)

Max Activating Token Index: 709

Text #9

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1548839 (The Pile)

Max Activating Token Index: 539

Text #10

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1821833 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8571. Min Act: -0.0000

Data Index: 201219 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1936227 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8230. Min Act: -0.0000

Data Index: 499935 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8762. Min Act: -0.0000

Data Index: 146840 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1786428 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.7856. Min Act: -0.0000

Data Index: 642567 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1725792 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1916381 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8052. Min Act: -0.0000

Data Index: 990880 (The Pile)

Max Activating Token Index: 479