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

Dataset: The Pile

Neuron 1285 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: 0.9093. Min Range: -0.9093

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1189757 (The Pile)

Max Activating Token Index: 570

Text #1

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1579266 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7349. Min Act: -0.0000

Data Index: 252125 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7521. Min Act: -0.0000

Data Index: 65611 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7777. Min Act: -0.0000

Data Index: 782462 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1417202 (The Pile)

Max Activating Token Index: 1008

Text #6

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7114. Min Act: -0.0000

Data Index: 460128 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1435833 (The Pile)

Max Activating Token Index: 342

Text #8

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7131. Min Act: -0.0000

Data Index: 407144 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.6460. Min Act: -0.0000

Data Index: 191276 (The Pile)

Max Activating Token Index: 984

Text #10

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.6914. Min Act: -0.0000

Data Index: 435353 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.6104. Min Act: -0.0000

Data Index: 343633 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1939423 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.6221. Min Act: -0.0000

Data Index: 970374 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1831755 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.5917. Min Act: -0.0000

Data Index: 696365 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.6063. Min Act: -0.0000

Data Index: 106752 (The Pile)

Max Activating Token Index: 411

Text #17

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1965468 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1029282 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1838525 (The Pile)

Max Activating Token Index: 628