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

Dataset: The Pile

Neuron 2353 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: 1.1304. Min Range: -1.1304

Max Act: 1.1304. Min Act: -0.0000

Data Index: 6932 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 1.1304. Min Range: -1.1304

Max Act: 1.0772. Min Act: -0.0000

Data Index: 639216 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1952700 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1559730 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9329. Min Act: -0.0000

Data Index: 73739 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9215. Min Act: -0.0000

Data Index: 26939 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1251915 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9381. Min Act: -0.0000

Data Index: 2713 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1530155 (The Pile)

Max Activating Token Index: 889

Text #9

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1753329 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.8064. Min Act: -0.0000

Data Index: 744998 (The Pile)

Max Activating Token Index: 652

Text #11

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1909087 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1562760 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1598964 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1532515 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.7541. Min Act: -0.0000

Data Index: 387921 (The Pile)

Max Activating Token Index: 755

Text #16

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.7926. Min Act: -0.0000

Data Index: 221534 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1786891 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.7506. Min Act: 0.0000

Data Index: 734167 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.7567. Min Act: -0.0000

Data Index: 831001 (The Pile)

Max Activating Token Index: 600