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

Dataset: The Pile

Neuron 3003 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: 0.9052. Min Range: -0.9052

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1318354 (The Pile)

Max Activating Token Index: 186

Text #1

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.8312. Min Act: -0.0000

Data Index: 907753 (The Pile)

Max Activating Token Index: 244

Text #2

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7444. Min Act: -0.0000

Data Index: 220960 (The Pile)

Max Activating Token Index: 895

Text #3

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.9052. Min Act: -0.0000

Data Index: 1436891 (The Pile)

Max Activating Token Index: 588

Text #4

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1599528 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1518066 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1948155 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7245. Min Act: -0.0000

Data Index: 964018 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1066288 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7139. Min Act: -0.0000

Data Index: 28796 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7344. Min Act: -0.0000

Data Index: 898471 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1775422 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7614. Min Act: -0.0000

Data Index: 693829 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1654260 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1799848 (The Pile)

Max Activating Token Index: 507

Text #15

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1938287 (The Pile)

Max Activating Token Index: 751

Text #16

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7417. Min Act: -0.0000

Data Index: 711097 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1836956 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.6753. Min Act: -0.0000

Data Index: 639202 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1130096 (The Pile)

Max Activating Token Index: 363