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

Dataset: The Pile

Neuron 4307 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1262. Min Range: -1.1262

Max Act: 1.1262. Min Act: -0.0000

Data Index: 1489922 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 1.1262. Min Range: -1.1262

Max Act: 1.1255. Min Act: -0.0000

Data Index: 1669144 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 1.1262. Min Range: -1.1262

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1695775 (The Pile)

Max Activating Token Index: 440

Text #3

Max Range: 1.1262. Min Range: -1.1262

Max Act: 1.0390. Min Act: -0.0000

Data Index: 955072 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9954. Min Act: -0.0000

Data Index: 220743 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 1.1262. Min Range: -1.1262

Max Act: 1.0264. Min Act: -0.0000

Data Index: 148953 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9898. Min Act: -0.0000

Data Index: 1422764 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9308. Min Act: -0.0000

Data Index: 195022 (The Pile)

Max Activating Token Index: 841

Text #8

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1004232 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9755. Min Act: -0.0000

Data Index: 577064 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 1.1262. Min Range: -1.1262

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1120273 (The Pile)

Max Activating Token Index: 716

Text #11

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9153. Min Act: -0.0000

Data Index: 605375 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1809972 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1969215 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8962. Min Act: -0.0000

Data Index: 367834 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1355308 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8617. Min Act: -0.0000

Data Index: 260786 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1523139 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1056990 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1250409 (The Pile)

Max Activating Token Index: 378