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

Dataset: The Pile

Neuron 2477 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.8909. Min Act: -0.0000

Data Index: 971152 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.8074. Min Act: 0.0000

Data Index: 1134267 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7990. Min Act: -0.0000

Data Index: 46820 (The Pile)

Max Activating Token Index: 919

Text #3

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.8069. Min Act: 0.0000

Data Index: 1020214 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1299051 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7715. Min Act: 0.0000

Data Index: 658302 (The Pile)

Max Activating Token Index: 304

Text #6

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7428. Min Act: -0.0000

Data Index: 505918 (The Pile)

Max Activating Token Index: 823

Text #7

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7565. Min Act: -0.0000

Data Index: 105764 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7491. Min Act: -0.0000

Data Index: 205550 (The Pile)

Max Activating Token Index: 423

Text #9

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7509. Min Act: 0.0000

Data Index: 401957 (The Pile)

Max Activating Token Index: 590

Text #10

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7437. Min Act: -0.0000

Data Index: 205913 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7450. Min Act: 0.0000

Data Index: 1028304 (The Pile)

Max Activating Token Index: 919

Text #12

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7491. Min Act: -0.0000

Data Index: 573220 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1366447 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7126. Min Act: -0.0000

Data Index: 248647 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7323. Min Act: -0.0000

Data Index: 974388 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1573076 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7374. Min Act: -0.0000

Data Index: 515851 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7127. Min Act: -0.0000

Data Index: 239807 (The Pile)

Max Activating Token Index: 520

Text #19

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7079. Min Act: -0.0000

Data Index: 641737 (The Pile)

Max Activating Token Index: 68