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

Dataset: The Pile

Neuron 1103 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2506. Min Range: -4.2506

Max Act: 4.2506. Min Act: -0.0000

Data Index: 1282809 (The Pile)

Max Activating Token Index: 920

Text #1

Max Range: 4.2506. Min Range: -4.2506

Max Act: 3.7630. Min Act: -0.0000

Data Index: 196260 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 4.2506. Min Range: -4.2506

Max Act: 3.9910. Min Act: -0.0000

Data Index: 1586267 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 4.2506. Min Range: -4.2506

Max Act: 3.4169. Min Act: -0.0000

Data Index: 509425 (The Pile)

Max Activating Token Index: 408

Text #4

Max Range: 4.2506. Min Range: -4.2506

Max Act: 3.0286. Min Act: -0.0000

Data Index: 144034 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.9098. Min Act: -0.0000

Data Index: 1482090 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.8386. Min Act: -0.0000

Data Index: 165636 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.3251. Min Act: -0.0000

Data Index: 597925 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.6387. Min Act: -0.0000

Data Index: 1371170 (The Pile)

Max Activating Token Index: 617

Text #9

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.6527. Min Act: -0.0000

Data Index: 657477 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.6247. Min Act: -0.0000

Data Index: 1061261 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.3420. Min Act: -0.0000

Data Index: 552828 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.4524. Min Act: -0.0000

Data Index: 1281040 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.3717. Min Act: -0.0000

Data Index: 319402 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.4188. Min Act: -0.0000

Data Index: 1150872 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.4919. Min Act: -0.0000

Data Index: 290044 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.1691. Min Act: -0.0000

Data Index: 1887786 (The Pile)

Max Activating Token Index: 460

Text #17

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.3529. Min Act: -0.0000

Data Index: 1039476 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.2542. Min Act: -0.0000

Data Index: 158290 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 4.2506. Min Range: -4.2506

Max Act: 2.4766. Min Act: -0.0000

Data Index: 1639731 (The Pile)

Max Activating Token Index: 386