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

Dataset: The Pile

Neuron 26 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4672. Min Range: -3.4672

Max Act: 3.4672. Min Act: -0.0000

Data Index: 682630 (The Pile)

Max Activating Token Index: 371

Text #1

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.9748. Min Act: -0.0000

Data Index: 1735391 (The Pile)

Max Activating Token Index: 586

Text #2

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.6341. Min Act: -0.0000

Data Index: 595568 (The Pile)

Max Activating Token Index: 712

Text #3

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.6726. Min Act: -0.0000

Data Index: 1811363 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 3.4672. Min Range: -3.4672

Max Act: 3.0179. Min Act: -0.0000

Data Index: 848534 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.7763. Min Act: -0.0000

Data Index: 643432 (The Pile)

Max Activating Token Index: 810

Text #6

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.7300. Min Act: -0.0000

Data Index: 1743954 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 3.4672. Min Range: -3.4672

Max Act: 3.0069. Min Act: -0.0000

Data Index: 293594 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.8384. Min Act: -0.0000

Data Index: 1084541 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.3992. Min Act: -0.0000

Data Index: 775278 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.7503. Min Act: -0.0000

Data Index: 1273567 (The Pile)

Max Activating Token Index: 343

Text #11

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.9008. Min Act: -0.0000

Data Index: 60965 (The Pile)

Max Activating Token Index: 617

Text #12

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.5924. Min Act: -0.0000

Data Index: 1820477 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.5652. Min Act: -0.0000

Data Index: 544606 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.8888. Min Act: -0.0000

Data Index: 1790154 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.8210. Min Act: -0.0000

Data Index: 853361 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.2790. Min Act: -0.0000

Data Index: 448639 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.7969. Min Act: -0.0000

Data Index: 369645 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.5058. Min Act: -0.0000

Data Index: 766570 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 3.4672. Min Range: -3.4672

Max Act: 2.5950. Min Act: -0.0000

Data Index: 1093594 (The Pile)

Max Activating Token Index: 1008