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

Dataset: The Pile

Neuron 464 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2518. Min Range: -5.2518

Max Act: 5.2518. Min Act: -0.0000

Data Index: 690209 (The Pile)

Max Activating Token Index: 701

Text #1

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.8772. Min Act: -0.0000

Data Index: 1983282 (The Pile)

Max Activating Token Index: 84

Text #2

Max Range: 5.2518. Min Range: -5.2518

Max Act: 5.1897. Min Act: -0.0000

Data Index: 1784031 (The Pile)

Max Activating Token Index: 823

Text #3

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.5889. Min Act: -0.0000

Data Index: 991223 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.5161. Min Act: -0.0000

Data Index: 1160576 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.1120. Min Act: -0.0000

Data Index: 1316583 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.7350. Min Act: -0.0000

Data Index: 1083634 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.5640. Min Act: -0.0000

Data Index: 1677066 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.6637. Min Act: -0.0000

Data Index: 1478680 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.5226. Min Act: -0.0000

Data Index: 802869 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.3104. Min Act: -0.0000

Data Index: 1120364 (The Pile)

Max Activating Token Index: 783

Text #11

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.1234. Min Act: -0.0000

Data Index: 1574212 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.1883. Min Act: -0.0000

Data Index: 1106079 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.1815. Min Act: -0.0000

Data Index: 1861193 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.2019. Min Act: -0.0000

Data Index: 1733498 (The Pile)

Max Activating Token Index: 819

Text #15

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.3249. Min Act: -0.0000

Data Index: 1009399 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 5.2518. Min Range: -5.2518

Max Act: 3.9807. Min Act: -0.0000

Data Index: 1285059 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.6575. Min Act: -0.0000

Data Index: 1980435 (The Pile)

Max Activating Token Index: 992

Text #18

Max Range: 5.2518. Min Range: -5.2518

Max Act: 4.4909. Min Act: -0.0000

Data Index: 361407 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 5.2518. Min Range: -5.2518

Max Act: 3.6535. Min Act: -0.0000

Data Index: 1196067 (The Pile)

Max Activating Token Index: 921