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

Dataset: The Pile

Neuron 3165 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.9214. Min Act: -0.0000

Data Index: 607153 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.6756. Min Act: -0.0000

Data Index: 998006 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.5132. Min Act: -0.0000

Data Index: 1791006 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.4754. Min Act: -0.0000

Data Index: 1077306 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.4454. Min Act: -0.0000

Data Index: 453712 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.4921. Min Act: -0.0000

Data Index: 983787 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.4147. Min Act: -0.0000

Data Index: 1547397 (The Pile)

Max Activating Token Index: 451

Text #7

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.4816. Min Act: -0.0000

Data Index: 596421 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.3946. Min Act: -0.0000

Data Index: 980046 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.4245. Min Act: -0.0000

Data Index: 168350 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.3165. Min Act: -0.0000

Data Index: 1130296 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.3784. Min Act: -0.0000

Data Index: 681673 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.3319. Min Act: -0.0000

Data Index: 493656 (The Pile)

Max Activating Token Index: 938

Text #13

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.3496. Min Act: -0.0000

Data Index: 1867006 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1425569 (The Pile)

Max Activating Token Index: 242

Text #15

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.2677. Min Act: -0.0000

Data Index: 836901 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.2666. Min Act: -0.0000

Data Index: 1028694 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.3218. Min Act: -0.0000

Data Index: 1422716 (The Pile)

Max Activating Token Index: 275

Text #18

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.2386. Min Act: -0.0000

Data Index: 1742003 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 1.9214. Min Range: -1.9214

Max Act: 1.2651. Min Act: -0.0000

Data Index: 1655677 (The Pile)

Max Activating Token Index: 433