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

Dataset: The Pile

Neuron 475 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: 1.0441. Min Range: -1.0441

Max Act: 1.0441. Min Act: -0.0000

Data Index: 443458 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0259. Min Act: -0.0000

Data Index: 298318 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1952641 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1354501 (The Pile)

Max Activating Token Index: 518

Text #4

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9693. Min Act: -0.0000

Data Index: 833762 (The Pile)

Max Activating Token Index: 807

Text #5

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1262352 (The Pile)

Max Activating Token Index: 724

Text #6

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1352439 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1398111 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1246262 (The Pile)

Max Activating Token Index: 375

Text #9

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9063. Min Act: -0.0000

Data Index: 125098 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1508423 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8346. Min Act: -0.0000

Data Index: 1508213 (The Pile)

Max Activating Token Index: 519

Text #12

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1747928 (The Pile)

Max Activating Token Index: 721

Text #13

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1482932 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1373842 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1699599 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8043. Min Act: -0.0000

Data Index: 206698 (The Pile)

Max Activating Token Index: 570

Text #17

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1847318 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1180684 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1969527 (The Pile)

Max Activating Token Index: 130