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

Dataset: The Pile

Neuron 1038 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.2603. Min Act: -0.0000

Data Index: 1133915 (The Pile)

Max Activating Token Index: 926

Text #1

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.2762. Min Act: -0.0000

Data Index: 1465793 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0597. Min Act: 0.0000

Data Index: 1381878 (The Pile)

Max Activating Token Index: 319

Text #3

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0286. Min Act: -0.0000

Data Index: 1023666 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.7686. Min Act: -0.0000

Data Index: 1475486 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.6395. Min Act: -0.0000

Data Index: 951931 (The Pile)

Max Activating Token Index: 201

Text #6

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.3449. Min Act: -0.0000

Data Index: 1819283 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.6308. Min Act: -0.0000

Data Index: 1587327 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.7667. Min Act: -0.0000

Data Index: 178778 (The Pile)

Max Activating Token Index: 759

Text #9

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.1900. Min Act: -0.0000

Data Index: 1352688 (The Pile)

Max Activating Token Index: 935

Text #10

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.2858. Min Act: -0.0000

Data Index: 580235 (The Pile)

Max Activating Token Index: 816

Text #11

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.0978. Min Act: -0.0000

Data Index: 44388 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.3535. Min Act: -0.0000

Data Index: 431573 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.0744. Min Act: -0.0000

Data Index: 1610468 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.1181. Min Act: -0.0000

Data Index: 1221055 (The Pile)

Max Activating Token Index: 163

Text #15

Max Range: 4.2762. Min Range: -4.2762

Max Act: 2.6135. Min Act: -0.0000

Data Index: 615270 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.1428. Min Act: -0.0000

Data Index: 1315689 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 4.2762. Min Range: -4.2762

Max Act: 3.0623. Min Act: -0.0000

Data Index: 87412 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 4.2762. Min Range: -4.2762

Max Act: 2.9847. Min Act: -0.0000

Data Index: 296711 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 4.2762. Min Range: -4.2762

Max Act: 2.9837. Min Act: -0.0000

Data Index: 536412 (The Pile)

Max Activating Token Index: 461