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

Dataset: The Pile

Neuron 4753 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2336. Min Act: -0.0000

Data Index: 197032 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.0441. Min Act: -0.0000

Data Index: 1244041 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.0371. Min Act: -0.0000

Data Index: 1428224 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.0117. Min Act: -0.0000

Data Index: 443413 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9030. Min Act: -0.0000

Data Index: 50437 (The Pile)

Max Activating Token Index: 583

Text #5

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.0212. Min Act: -0.0000

Data Index: 317740 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8999. Min Act: -0.0000

Data Index: 818910 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1928623 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1844654 (The Pile)

Max Activating Token Index: 710

Text #9

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9500. Min Act: -0.0000

Data Index: 40281 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1669174 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1382101 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9242. Min Act: -0.0000

Data Index: 347235 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9456. Min Act: -0.0000

Data Index: 606601 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.7302. Min Act: -0.0000

Data Index: 852962 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1898081 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1698892 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1247257 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8455. Min Act: -0.0000

Data Index: 866763 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9137. Min Act: -0.0000

Data Index: 464413 (The Pile)

Max Activating Token Index: 387