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

Dataset: The Pile

Neuron 3832 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0701. Min Range: -1.0701

Max Act: 1.0701. Min Act: -0.0000

Data Index: 240734 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.9270. Min Act: -0.0000

Data Index: 867714 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.8795. Min Act: -0.0000

Data Index: 423896 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.8085. Min Act: -0.0000

Data Index: 655961 (The Pile)

Max Activating Token Index: 152

Text #4

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1228560 (The Pile)

Max Activating Token Index: 785

Text #5

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7612. Min Act: -0.0000

Data Index: 216503 (The Pile)

Max Activating Token Index: 173

Text #6

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.8410. Min Act: -0.0000

Data Index: 8624 (The Pile)

Max Activating Token Index: 558

Text #7

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1678190 (The Pile)

Max Activating Token Index: 106

Text #8

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.8062. Min Act: -0.0000

Data Index: 796527 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7329. Min Act: -0.0000

Data Index: 526637 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1642210 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7157. Min Act: -0.0000

Data Index: 215358 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1052798 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6235. Min Act: -0.0000

Data Index: 578675 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6387. Min Act: -0.0000

Data Index: 823661 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1954292 (The Pile)

Max Activating Token Index: 426

Text #16

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6303. Min Act: -0.0000

Data Index: 396424 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1086330 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1990075 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6310. Min Act: -0.0000

Data Index: 690152 (The Pile)

Max Activating Token Index: 804