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

Dataset: The Pile

Neuron 4272 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: 1.0184. Min Range: -1.0184

Max Act: 1.0184. Min Act: -0.0000

Data Index: 19231 (The Pile)

Max Activating Token Index: 510

Text #1

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7844. Min Act: 0.0000

Data Index: 1698900 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7612. Min Act: -0.0000

Data Index: 225172 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1505760 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1707046 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1898749 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7310. Min Act: -0.0000

Data Index: 577666 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1135134 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1199303 (The Pile)

Max Activating Token Index: 341

Text #9

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1744720 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7563. Min Act: 0.0000

Data Index: 945528 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7314. Min Act: -0.0000

Data Index: 498595 (The Pile)

Max Activating Token Index: 752

Text #12

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7051. Min Act: -0.0000

Data Index: 745337 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1733160 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1766667 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.6918. Min Act: -0.0000

Data Index: 30124 (The Pile)

Max Activating Token Index: 973

Text #16

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1672999 (The Pile)

Max Activating Token Index: 364

Text #17

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7363. Min Act: -0.0000

Data Index: 60319 (The Pile)

Max Activating Token Index: 450

Text #18

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1998853 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1171467 (The Pile)

Max Activating Token Index: 586