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

Dataset: The Pile

Neuron 44 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: 1.1604. Min Range: -1.1604

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1608550 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1672889 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.0234. Min Act: -0.0000

Data Index: 498883 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1328497 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9775. Min Act: -0.0000

Data Index: 310945 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1754954 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.0037. Min Act: -0.0000

Data Index: 269501 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9394. Min Act: -0.0000

Data Index: 377355 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9265. Min Act: -0.0000

Data Index: 969231 (The Pile)

Max Activating Token Index: 382

Text #9

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1277510 (The Pile)

Max Activating Token Index: 411

Text #10

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9099. Min Act: -0.0000

Data Index: 564545 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1090604 (The Pile)

Max Activating Token Index: 944

Text #12

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1490012 (The Pile)

Max Activating Token Index: 926

Text #13

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1519425 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1023845 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8969. Min Act: -0.0000

Data Index: 1659749 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.7946. Min Act: -0.0000

Data Index: 664063 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1530967 (The Pile)

Max Activating Token Index: 73

Text #18

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1028461 (The Pile)

Max Activating Token Index: 955

Text #19

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8607. Min Act: -0.0000

Data Index: 541236 (The Pile)

Max Activating Token Index: 310