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

Dataset: The Pile

Neuron 448 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: 0.6224. Min Range: -0.6224

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1149686 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5274. Min Act: -0.0001

Data Index: 241830 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5294. Min Act: -0.0000

Data Index: 32986 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1447250 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4516. Min Act: -0.0000

Data Index: 449252 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1384319 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4477. Min Act: -0.0000

Data Index: 600638 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4581. Min Act: -0.0000

Data Index: 760676 (The Pile)

Max Activating Token Index: 810

Text #8

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1743939 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4533. Min Act: -0.0000

Data Index: 76713 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4101. Min Act: -0.0000

Data Index: 593460 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4560. Min Act: -0.0000

Data Index: 98161 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4699. Min Act: -0.0000

Data Index: 154134 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1248627 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4479. Min Act: -0.0000

Data Index: 326987 (The Pile)

Max Activating Token Index: 795

Text #15

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1339451 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4260. Min Act: -0.0000

Data Index: 235024 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1736075 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1696555 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4407. Min Act: -0.0000

Data Index: 558706 (The Pile)

Max Activating Token Index: 493