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

Dataset: The Pile

Neuron 3149 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.8318. Min Act: -0.0000

Data Index: 454367 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.6202. Min Act: -0.0000

Data Index: 1312588 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.6487. Min Act: -0.0000

Data Index: 14490 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4881. Min Act: -0.0000

Data Index: 551672 (The Pile)

Max Activating Token Index: 529

Text #4

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.5952. Min Act: -0.0000

Data Index: 987135 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.5588. Min Act: -0.0000

Data Index: 1801701 (The Pile)

Max Activating Token Index: 27

Text #6

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4141. Min Act: -0.0000

Data Index: 1897411 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.5634. Min Act: -0.0000

Data Index: 1315381 (The Pile)

Max Activating Token Index: 763

Text #8

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3789. Min Act: -0.0000

Data Index: 1020790 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4475. Min Act: -0.0000

Data Index: 532602 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4263. Min Act: -0.0000

Data Index: 768745 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4375. Min Act: -0.0000

Data Index: 622266 (The Pile)

Max Activating Token Index: 454

Text #12

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4370. Min Act: -0.0000

Data Index: 775873 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1949616 (The Pile)

Max Activating Token Index: 860

Text #14

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.2756. Min Act: -0.0000

Data Index: 1783813 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3768. Min Act: -0.0000

Data Index: 908551 (The Pile)

Max Activating Token Index: 811

Text #16

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4178. Min Act: -0.0000

Data Index: 1094321 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3806. Min Act: -0.0000

Data Index: 403616 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1592507 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3431. Min Act: -0.0000

Data Index: 1110913 (The Pile)

Max Activating Token Index: 596