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

Dataset: The Pile

Neuron 1634 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: 1.3487. Min Range: -1.3487

Max Act: 1.3487. Min Act: -0.0000

Data Index: 1075250 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2980. Min Act: -0.0000

Data Index: 1865769 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1101388 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1870496 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1689052 (The Pile)

Max Activating Token Index: 718

Text #5

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.9482. Min Act: -0.0000

Data Index: 102468 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.8730. Min Act: -0.0000

Data Index: 687537 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1885401 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.8292. Min Act: -0.0000

Data Index: 318697 (The Pile)

Max Activating Token Index: 767

Text #9

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.7731. Min Act: -0.0000

Data Index: 53749 (The Pile)

Max Activating Token Index: 904

Text #10

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1149900 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.7510. Min Act: -0.0000

Data Index: 69155 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.7875. Min Act: -0.0000

Data Index: 185528 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1930254 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.6767. Min Act: -0.0000

Data Index: 934913 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.6688. Min Act: -0.0000

Data Index: 304511 (The Pile)

Max Activating Token Index: 52

Text #16

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.6954. Min Act: -0.0000

Data Index: 80536 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1253756 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.6912. Min Act: -0.0000

Data Index: 383205 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.6737. Min Act: -0.0000

Data Index: 99613 (The Pile)

Max Activating Token Index: 259