Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 216 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1216. Min Act: -0.0000

Data Index: 27414 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1845629 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1234. Min Act: -0.0000

Data Index: 783836 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1155. Min Act: 0.0000

Data Index: 383061 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1730807 (The Pile)

Max Activating Token Index: 381

Text #5

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1674256 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0958. Min Act: -0.0000

Data Index: 598624 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1022. Min Act: -0.0000

Data Index: 966471 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1014. Min Act: -0.0000

Data Index: 599951 (The Pile)

Max Activating Token Index: 464

Text #9

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0924. Min Act: -0.0000

Data Index: 315955 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0942. Min Act: -0.0000

Data Index: 474367 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1686280 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1030162 (The Pile)

Max Activating Token Index: 325

Text #13

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0915. Min Act: 0.0000

Data Index: 1759479 (The Pile)

Max Activating Token Index: 841

Text #14

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0951. Min Act: 0.0000

Data Index: 378752 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0911. Min Act: -0.0000

Data Index: 355653 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0908. Min Act: -0.0000

Data Index: 552945 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1015713 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1184516 (The Pile)

Max Activating Token Index: 206

Text #19

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1772129 (The Pile)

Max Activating Token Index: 975