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

Dataset: The Pile

Neuron 4876 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: 0.6652. Min Range: -0.6652

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1539255 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.6628. Min Act: -0.0000

Data Index: 736823 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.6071. Min Act: -0.0000

Data Index: 696397 (The Pile)

Max Activating Token Index: 211

Text #3

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1378045 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4803. Min Act: -0.0000

Data Index: 474033 (The Pile)

Max Activating Token Index: 604

Text #5

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4616. Min Act: -0.0000

Data Index: 247763 (The Pile)

Max Activating Token Index: 327

Text #6

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4512. Min Act: -0.0000

Data Index: 125618 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1668004 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4532. Min Act: -0.0000

Data Index: 892775 (The Pile)

Max Activating Token Index: 334

Text #9

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4309. Min Act: -0.0000

Data Index: 693982 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1140320 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4189. Min Act: -0.0000

Data Index: 895257 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1894209 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1667643 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1134766 (The Pile)

Max Activating Token Index: 546

Text #15

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.3685. Min Act: -0.0000

Data Index: 639143 (The Pile)

Max Activating Token Index: 865

Text #16

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4342. Min Act: -0.0000

Data Index: 279697 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.3775. Min Act: -0.0000

Data Index: 916513 (The Pile)

Max Activating Token Index: 75

Text #18

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.3980. Min Act: -0.0000

Data Index: 902447 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4018. Min Act: -0.0000

Data Index: 78334 (The Pile)

Max Activating Token Index: 253