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

Dataset: The Pile

Neuron 1223 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.5335. Min Act: -0.0000

Data Index: 1766765 (The Pile)

Max Activating Token Index: 354

Text #1

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.6700. Min Act: -0.0000

Data Index: 1644133 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.7032. Min Act: -0.0000

Data Index: 1322532 (The Pile)

Max Activating Token Index: 750

Text #3

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.8205. Min Act: -0.0000

Data Index: 682603 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.3694. Min Act: -0.0000

Data Index: 235639 (The Pile)

Max Activating Token Index: 234

Text #5

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.3827. Min Act: -0.0000

Data Index: 1567207 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.3161. Min Act: -0.0000

Data Index: 832263 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.3701. Min Act: -0.0000

Data Index: 1270604 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.4359. Min Act: -0.0000

Data Index: 1525699 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.3363. Min Act: -0.0000

Data Index: 1760915 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.3351. Min Act: -0.0000

Data Index: 1062315 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1039833 (The Pile)

Max Activating Token Index: 798

Text #12

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.2884. Min Act: -0.0000

Data Index: 312531 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.2966. Min Act: -0.0000

Data Index: 754071 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.2767. Min Act: -0.0000

Data Index: 16122 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.1750. Min Act: -0.0000

Data Index: 593335 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.2801. Min Act: -0.0000

Data Index: 561648 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.2508. Min Act: -0.0000

Data Index: 566912 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.2999. Min Act: -0.0000

Data Index: 760289 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1732527 (The Pile)

Max Activating Token Index: 261