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

Dataset: The Pile

Neuron 2425 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1221. Min Range: -1.1221

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1009500 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 1.1221. Min Range: -1.1221

Max Act: 1.1221. Min Act: -0.0000

Data Index: 180916 (The Pile)

Max Activating Token Index: 983

Text #2

Max Range: 1.1221. Min Range: -1.1221

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1159805 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9639. Min Act: -0.0000

Data Index: 174031 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1518137 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9499. Min Act: -0.0000

Data Index: 177410 (The Pile)

Max Activating Token Index: 250

Text #6

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9385. Min Act: -0.0000

Data Index: 216872 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1164753 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9114. Min Act: -0.0000

Data Index: 668447 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1492293 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8865. Min Act: -0.0000

Data Index: 897492 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1317240 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8989. Min Act: -0.0000

Data Index: 10130 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1836833 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8651. Min Act: -0.0000

Data Index: 176634 (The Pile)

Max Activating Token Index: 811

Text #15

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1696369 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1173032 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8583. Min Act: -0.0000

Data Index: 528596 (The Pile)

Max Activating Token Index: 394

Text #18

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1890701 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1789832 (The Pile)

Max Activating Token Index: 383