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

Dataset: The Pile

Neuron 3349 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: 3.9105. Min Range: -3.9105

Max Act: 3.7683. Min Act: -0.0000

Data Index: 1925794 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.5419. Min Act: -0.0000

Data Index: 934235 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.9105. Min Act: -0.0000

Data Index: 1146266 (The Pile)

Max Activating Token Index: 357

Text #3

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.5357. Min Act: -0.0000

Data Index: 1814507 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.2609. Min Act: -0.0000

Data Index: 1599684 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.3149. Min Act: -0.0000

Data Index: 1281571 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.1010. Min Act: -0.0000

Data Index: 1488632 (The Pile)

Max Activating Token Index: 851

Text #7

Max Range: 3.9105. Min Range: -3.9105

Max Act: 2.6313. Min Act: -0.0000

Data Index: 1442849 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 3.9105. Min Range: -3.9105

Max Act: 2.9282. Min Act: -0.0000

Data Index: 401476 (The Pile)

Max Activating Token Index: 806

Text #9

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.0446. Min Act: -0.0000

Data Index: 839202 (The Pile)

Max Activating Token Index: 766

Text #10

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.1653. Min Act: -0.0000

Data Index: 378631 (The Pile)

Max Activating Token Index: 263

Text #11

Max Range: 3.9105. Min Range: -3.9105

Max Act: 2.7861. Min Act: -0.0000

Data Index: 381623 (The Pile)

Max Activating Token Index: 572

Text #12

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.0346. Min Act: -0.0000

Data Index: 367584 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 3.9105. Min Range: -3.9105

Max Act: 2.8801. Min Act: -0.0000

Data Index: 939877 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.2168. Min Act: -0.0000

Data Index: 832068 (The Pile)

Max Activating Token Index: 718

Text #15

Max Range: 3.9105. Min Range: -3.9105

Max Act: 2.9796. Min Act: -0.0000

Data Index: 153914 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 3.9105. Min Range: -3.9105

Max Act: 2.6859. Min Act: -0.0000

Data Index: 1128875 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 3.9105. Min Range: -3.9105

Max Act: 2.6706. Min Act: -0.0000

Data Index: 1661672 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 3.9105. Min Range: -3.9105

Max Act: 2.7965. Min Act: -0.0000

Data Index: 767722 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 3.9105. Min Range: -3.9105

Max Act: 2.3949. Min Act: -0.0000

Data Index: 1670254 (The Pile)

Max Activating Token Index: 631