Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3160 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.6225. Min Act: -0.0000

Data Index: 63728 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1419368 (The Pile)

Max Activating Token Index: 471

Text #2

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1681564 (The Pile)

Max Activating Token Index: 794

Text #3

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4271. Min Act: -0.0000

Data Index: 55230 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4564. Min Act: -0.0000

Data Index: 294191 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5159. Min Act: -0.0000

Data Index: 703939 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1435306 (The Pile)

Max Activating Token Index: 635

Text #7

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4105. Min Act: -0.0000

Data Index: 121204 (The Pile)

Max Activating Token Index: 399

Text #8

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5074. Min Act: -0.0000

Data Index: 972055 (The Pile)

Max Activating Token Index: 635

Text #9

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1410368 (The Pile)

Max Activating Token Index: 609

Text #10

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4368. Min Act: -0.0000

Data Index: 44452 (The Pile)

Max Activating Token Index: 645

Text #11

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4322. Min Act: -0.0000

Data Index: 530767 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4450. Min Act: -0.0000

Data Index: 251262 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4061. Min Act: -0.0000

Data Index: 897329 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4305. Min Act: -0.0000

Data Index: 30813 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4850. Min Act: -0.0000

Data Index: 405400 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4414. Min Act: -0.0000

Data Index: 294917 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1659994 (The Pile)

Max Activating Token Index: 27

Text #18

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4124. Min Act: -0.0000

Data Index: 761886 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1312377 (The Pile)

Max Activating Token Index: 653