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

Dataset: The Pile

Neuron 1483 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.4902. Min Act: -0.0000

Data Index: 590533 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.3360. Min Act: -0.0000

Data Index: 1665401 (The Pile)

Max Activating Token Index: 183

Text #2

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.9552. Min Act: -0.0000

Data Index: 341900 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.0491. Min Act: -0.0000

Data Index: 967159 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.5925. Min Act: -0.0000

Data Index: 1191483 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.7841. Min Act: -0.0000

Data Index: 660126 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.8746. Min Act: -0.0000

Data Index: 735845 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.5412. Min Act: -0.0000

Data Index: 1639553 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.3542. Min Act: -0.0000

Data Index: 69733 (The Pile)

Max Activating Token Index: 586

Text #9

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.5653. Min Act: -0.0001

Data Index: 116961 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.3071. Min Act: -0.0000

Data Index: 875153 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.3028. Min Act: -0.0000

Data Index: 106043 (The Pile)

Max Activating Token Index: 593

Text #12

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.3995. Min Act: -0.0000

Data Index: 1890328 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.3899. Min Act: -0.0000

Data Index: 1396170 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.2772. Min Act: -0.0000

Data Index: 1466388 (The Pile)

Max Activating Token Index: 266

Text #15

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.2695. Min Act: -0.0000

Data Index: 627347 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.2553. Min Act: -0.0000

Data Index: 1773729 (The Pile)

Max Activating Token Index: 283

Text #17

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.3725. Min Act: -0.0000

Data Index: 631658 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.1960. Min Act: -0.0000

Data Index: 565154 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.0977. Min Act: -0.0000

Data Index: 467862 (The Pile)

Max Activating Token Index: 1003