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

Dataset: The Pile

Neuron 51 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8358. Min Range: -1.8358

Max Act: 1.8358. Min Act: -0.0000

Data Index: 143893 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 1.8358. Min Range: -1.8358

Max Act: 1.4549. Min Act: -0.0000

Data Index: 1725788 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 1.8358. Min Range: -1.8358

Max Act: 1.2159. Min Act: -0.0000

Data Index: 962600 (The Pile)

Max Activating Token Index: 529

Text #3

Max Range: 1.8358. Min Range: -1.8358

Max Act: 1.0926. Min Act: -0.0000

Data Index: 197078 (The Pile)

Max Activating Token Index: 325

Text #4

Max Range: 1.8358. Min Range: -1.8358

Max Act: 1.0026. Min Act: -0.0000

Data Index: 1979405 (The Pile)

Max Activating Token Index: 754

Text #5

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1749397 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.9645. Min Act: -0.0000

Data Index: 155430 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.9763. Min Act: -0.0000

Data Index: 721999 (The Pile)

Max Activating Token Index: 782

Text #8

Max Range: 1.8358. Min Range: -1.8358

Max Act: 1.0662. Min Act: -0.0000

Data Index: 809627 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1943957 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 1.8358. Min Range: -1.8358

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1012205 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.9768. Min Act: -0.0000

Data Index: 1398086 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1550679 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 1.8358. Min Range: -1.8358

Max Act: 1.0295. Min Act: -0.0000

Data Index: 443353 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1878751 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.9757. Min Act: -0.0000

Data Index: 785902 (The Pile)

Max Activating Token Index: 742

Text #16

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.8989. Min Act: -0.0000

Data Index: 241727 (The Pile)

Max Activating Token Index: 30

Text #17

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1223762 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.9020. Min Act: -0.0000

Data Index: 30605 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 1.8358. Min Range: -1.8358

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1105098 (The Pile)

Max Activating Token Index: 154