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

Dataset: The Pile

Neuron 1466 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: 1.1633. Min Range: -1.1633

Max Act: 1.1633. Min Act: -0.0000

Data Index: 227881 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9957. Min Act: -0.0000

Data Index: 391825 (The Pile)

Max Activating Token Index: 676

Text #2

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1119. Min Act: -0.0000

Data Index: 11326 (The Pile)

Max Activating Token Index: 662

Text #3

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0985. Min Act: -0.0000

Data Index: 195445 (The Pile)

Max Activating Token Index: 140

Text #4

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1295. Min Act: -0.0000

Data Index: 230094 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1600821 (The Pile)

Max Activating Token Index: 698

Text #6

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1482499 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9295. Min Act: -0.0000

Data Index: 403070 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1184555 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1883595 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9254. Min Act: -0.0000

Data Index: 881268 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1096208 (The Pile)

Max Activating Token Index: 608

Text #12

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9062. Min Act: -0.0000

Data Index: 220636 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1016598 (The Pile)

Max Activating Token Index: 541

Text #14

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1478245 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8701. Min Act: -0.0000

Data Index: 933032 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8894. Min Act: -0.0000

Data Index: 372530 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1084355 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9302. Min Act: -0.0000

Data Index: 435046 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1050619 (The Pile)

Max Activating Token Index: 241