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

Dataset: The Pile

Neuron 945 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: 0.3374. Min Range: -0.3374

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1430798 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.3374. Min Act: -0.0000

Data Index: 120854 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.3147. Min Act: -0.0000

Data Index: 420854 (The Pile)

Max Activating Token Index: 313

Text #3

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1823745 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2436. Min Act: -0.0000

Data Index: 474927 (The Pile)

Max Activating Token Index: 274

Text #5

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1009891 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2827. Min Act: -0.0000

Data Index: 8233 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1557580 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2310. Min Act: -0.0000

Data Index: 861171 (The Pile)

Max Activating Token Index: 437

Text #9

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2140. Min Act: -0.0000

Data Index: 159884 (The Pile)

Max Activating Token Index: 136

Text #10

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2073. Min Act: -0.0000

Data Index: 754807 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1126293 (The Pile)

Max Activating Token Index: 710

Text #12

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1463020 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1876729 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2071. Min Act: -0.0000

Data Index: 381147 (The Pile)

Max Activating Token Index: 477

Text #15

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1074413 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1969137 (The Pile)

Max Activating Token Index: 197

Text #17

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1093115 (The Pile)

Max Activating Token Index: 517

Text #18

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1515931 (The Pile)

Max Activating Token Index: 562

Text #19

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.1919. Min Act: -0.0000

Data Index: 501375 (The Pile)

Max Activating Token Index: 167