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

Dataset: The Pile

Neuron 1021 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: 3.9517. Min Range: -3.9517

Max Act: 3.9517. Min Act: -0.0000

Data Index: 1801167 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.1549. Min Act: -0.0000

Data Index: 734424 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.9600. Min Act: -0.0000

Data Index: 146767 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.8048. Min Act: -0.0000

Data Index: 407204 (The Pile)

Max Activating Token Index: 544

Text #4

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.8874. Min Act: -0.0000

Data Index: 1641816 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.8753. Min Act: -0.0000

Data Index: 387703 (The Pile)

Max Activating Token Index: 756

Text #6

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.0876. Min Act: -0.0000

Data Index: 1551760 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.8177. Min Act: -0.0000

Data Index: 229535 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.5439. Min Act: -0.0000

Data Index: 278348 (The Pile)

Max Activating Token Index: 208

Text #9

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.0500. Min Act: -0.0000

Data Index: 164154 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.0524. Min Act: -0.0000

Data Index: 1288913 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.7476. Min Act: -0.0000

Data Index: 677112 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.9952. Min Act: -0.0000

Data Index: 1742551 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.9907. Min Act: -0.0000

Data Index: 810208 (The Pile)

Max Activating Token Index: 858

Text #14

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.8416. Min Act: -0.0000

Data Index: 1625184 (The Pile)

Max Activating Token Index: 925

Text #15

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.6957. Min Act: -0.0000

Data Index: 874571 (The Pile)

Max Activating Token Index: 56

Text #16

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.8093. Min Act: -0.0000

Data Index: 1381274 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 3.9517. Min Range: -3.9517

Max Act: 2.9189. Min Act: -0.0000

Data Index: 1888996 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.0634. Min Act: -0.0000

Data Index: 1648636 (The Pile)

Max Activating Token Index: 608

Text #19

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.0594. Min Act: -0.0000

Data Index: 1086126 (The Pile)

Max Activating Token Index: 166