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

Dataset: The Pile

Neuron 4285 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: 0.8966. Min Range: -0.8966

Max Act: 0.8966. Min Act: -0.0000

Data Index: 965116 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1635443 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6642. Min Act: -0.0000

Data Index: 445939 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5902. Min Act: -0.0000

Data Index: 745523 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1367168 (The Pile)

Max Activating Token Index: 544

Text #5

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6241. Min Act: -0.0000

Data Index: 288503 (The Pile)

Max Activating Token Index: 321

Text #6

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1722406 (The Pile)

Max Activating Token Index: 544

Text #7

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1187326 (The Pile)

Max Activating Token Index: 860

Text #8

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6285. Min Act: -0.0000

Data Index: 644191 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6538. Min Act: -0.0000

Data Index: 381526 (The Pile)

Max Activating Token Index: 764

Text #10

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1630460 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1384005 (The Pile)

Max Activating Token Index: 656

Text #12

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1922504 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1680569 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1267194 (The Pile)

Max Activating Token Index: 815

Text #15

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5482. Min Act: -0.0000

Data Index: 614110 (The Pile)

Max Activating Token Index: 153

Text #16

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1280529 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5641. Min Act: -0.0000

Data Index: 884134 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1606988 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1296867 (The Pile)

Max Activating Token Index: 187