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

Dataset: The Pile

Neuron 2848 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.8582. Min Act: -0.0000

Data Index: 1393941 (The Pile)

Max Activating Token Index: 796

Text #1

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.4511. Min Act: -0.0000

Data Index: 1113372 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.1626. Min Act: -0.0000

Data Index: 1645394 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.2375. Min Act: -0.0000

Data Index: 1855736 (The Pile)

Max Activating Token Index: 1000

Text #4

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.9387. Min Act: -0.0000

Data Index: 1243998 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.9799. Min Act: -0.0000

Data Index: 1391237 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.8912. Min Act: -0.0000

Data Index: 1055952 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.1755. Min Act: -0.0000

Data Index: 1396086 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.8273. Min Act: -0.0000

Data Index: 10094 (The Pile)

Max Activating Token Index: 934

Text #9

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.8155. Min Act: -0.0000

Data Index: 653802 (The Pile)

Max Activating Token Index: 736

Text #10

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.7834. Min Act: -0.0000

Data Index: 851325 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.6800. Min Act: -0.0000

Data Index: 1491842 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.5534. Min Act: -0.0000

Data Index: 323330 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.3625. Min Act: -0.0000

Data Index: 1237797 (The Pile)

Max Activating Token Index: 982

Text #14

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.3181. Min Act: -0.0000

Data Index: 201686 (The Pile)

Max Activating Token Index: 941

Text #15

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.4436. Min Act: -0.0000

Data Index: 505854 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.6751. Min Act: -0.0000

Data Index: 491042 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.5389. Min Act: -0.0000

Data Index: 490518 (The Pile)

Max Activating Token Index: 809

Text #18

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.5198. Min Act: -0.0000

Data Index: 814413 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 3.8582. Min Range: -3.8582

Max Act: 2.3871. Min Act: -0.0000

Data Index: 1564338 (The Pile)

Max Activating Token Index: 114