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

Dataset: The Pile

Neuron 2690 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: 1.8606. Min Range: -1.8606

Max Act: 1.7607. Min Act: -0.0000

Data Index: 813690 (The Pile)

Max Activating Token Index: 917

Text #1

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.8309. Min Act: -0.0000

Data Index: 1862857 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.7254. Min Act: -0.0000

Data Index: 516986 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.7002. Min Act: -0.0000

Data Index: 1206824 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.8606. Min Act: -0.0000

Data Index: 1164166 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.7732. Min Act: -0.0000

Data Index: 1738145 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.7990. Min Act: -0.0000

Data Index: 1263179 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.6950. Min Act: -0.0000

Data Index: 225966 (The Pile)

Max Activating Token Index: 346

Text #8

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.5754. Min Act: -0.0000

Data Index: 1017769 (The Pile)

Max Activating Token Index: 323

Text #9

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4144. Min Act: -0.0000

Data Index: 129658 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.5554. Min Act: -0.0000

Data Index: 1037339 (The Pile)

Max Activating Token Index: 885

Text #11

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4438. Min Act: -0.0000

Data Index: 816077 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.3007. Min Act: -0.0000

Data Index: 1825161 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1850306 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.3716. Min Act: -0.0000

Data Index: 882791 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.3272. Min Act: -0.0000

Data Index: 802428 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4111. Min Act: -0.0000

Data Index: 768644 (The Pile)

Max Activating Token Index: 399

Text #17

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4862. Min Act: -0.0000

Data Index: 1408062 (The Pile)

Max Activating Token Index: 464

Text #18

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.3112. Min Act: -0.0000

Data Index: 925310 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.3540. Min Act: -0.0000

Data Index: 1843285 (The Pile)

Max Activating Token Index: 183