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

Dataset: The Pile

Neuron 1394 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: 1.2684. Min Range: -1.2684

Max Act: 1.2684. Min Act: -0.0000

Data Index: 497879 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 1.2684. Min Range: -1.2684

Max Act: 1.1543. Min Act: -0.0000

Data Index: 1841176 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.9904. Min Act: -0.0000

Data Index: 724101 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8368. Min Act: -0.0000

Data Index: 236663 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.9241. Min Act: -0.0000

Data Index: 147599 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8162. Min Act: -0.0000

Data Index: 574031 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8261. Min Act: -0.0000

Data Index: 395031 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8531. Min Act: -0.0000

Data Index: 738783 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1393415 (The Pile)

Max Activating Token Index: 63

Text #9

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8095. Min Act: -0.0000

Data Index: 165942 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8083. Min Act: -0.0000

Data Index: 445026 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1852215 (The Pile)

Max Activating Token Index: 98

Text #12

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.7792. Min Act: -0.0000

Data Index: 329850 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.7778. Min Act: -0.0000

Data Index: 569446 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8102. Min Act: -0.0000

Data Index: 815425 (The Pile)

Max Activating Token Index: 818

Text #15

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1722588 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.7336. Min Act: -0.0000

Data Index: 216520 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.7806. Min Act: -0.0000

Data Index: 230343 (The Pile)

Max Activating Token Index: 149

Text #18

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1775178 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.7799. Min Act: -0.0000

Data Index: 270647 (The Pile)

Max Activating Token Index: 320