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

Dataset: The Pile

Neuron 29 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: 3.1725. Min Range: -3.1725

Max Act: 3.1725. Min Act: -0.0000

Data Index: 839541 (The Pile)

Max Activating Token Index: 734

Text #1

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9390. Min Act: -0.0000

Data Index: 93402 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.0467. Min Act: -0.0000

Data Index: 145809 (The Pile)

Max Activating Token Index: 331

Text #3

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.3302. Min Act: -0.0000

Data Index: 1412406 (The Pile)

Max Activating Token Index: 937

Text #4

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.7347. Min Act: -0.0000

Data Index: 1539380 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.8502. Min Act: -0.0000

Data Index: 1036854 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.6324. Min Act: -0.0000

Data Index: 866443 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.4797. Min Act: -0.0000

Data Index: 846224 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.4446. Min Act: -0.0000

Data Index: 329222 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.4113. Min Act: -0.0000

Data Index: 1082813 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.3681. Min Act: -0.0000

Data Index: 1792884 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.4547. Min Act: -0.0000

Data Index: 359496 (The Pile)

Max Activating Token Index: 379

Text #12

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.4949. Min Act: -0.0000

Data Index: 217245 (The Pile)

Max Activating Token Index: 272

Text #13

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.3554. Min Act: -0.0000

Data Index: 572365 (The Pile)

Max Activating Token Index: 916

Text #14

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.3542. Min Act: -0.0000

Data Index: 129644 (The Pile)

Max Activating Token Index: 926

Text #15

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.3480. Min Act: -0.0000

Data Index: 1697171 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.1988. Min Act: -0.0000

Data Index: 420873 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.2956. Min Act: -0.0000

Data Index: 347822 (The Pile)

Max Activating Token Index: 753

Text #18

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.1013. Min Act: -0.0000

Data Index: 959113 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.2556. Min Act: -0.0000

Data Index: 657866 (The Pile)

Max Activating Token Index: 951