Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1606 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.9292. Min Act: -0.0000

Data Index: 488716 (The Pile)

Max Activating Token Index: 407

Text #1

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.9587. Min Act: -0.0000

Data Index: 226193 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8273. Min Act: -0.0000

Data Index: 137776 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7541. Min Act: -0.0000

Data Index: 646593 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8032. Min Act: -0.0000

Data Index: 1256335 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.9144. Min Act: -0.0000

Data Index: 588327 (The Pile)

Max Activating Token Index: 663

Text #6

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7779. Min Act: -0.0000

Data Index: 1718877 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.6736. Min Act: -0.0000

Data Index: 147943 (The Pile)

Max Activating Token Index: 251

Text #8

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8396. Min Act: -0.0000

Data Index: 54862 (The Pile)

Max Activating Token Index: 320

Text #9

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7673. Min Act: -0.0000

Data Index: 135830 (The Pile)

Max Activating Token Index: 463

Text #10

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.6482. Min Act: -0.0000

Data Index: 110810 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7219. Min Act: -0.0000

Data Index: 1856940 (The Pile)

Max Activating Token Index: 914

Text #12

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.6834. Min Act: -0.0000

Data Index: 1678311 (The Pile)

Max Activating Token Index: 801

Text #13

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8006. Min Act: -0.0000

Data Index: 217042 (The Pile)

Max Activating Token Index: 551

Text #14

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.5036. Min Act: -0.0000

Data Index: 1616484 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.5866. Min Act: -0.0000

Data Index: 1717871 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.6721. Min Act: -0.0000

Data Index: 1324430 (The Pile)

Max Activating Token Index: 930

Text #17

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.6897. Min Act: -0.0000

Data Index: 134844 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.6964. Min Act: -0.0000

Data Index: 72520 (The Pile)

Max Activating Token Index: 648

Text #19

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.6177. Min Act: -0.0000

Data Index: 643372 (The Pile)

Max Activating Token Index: 302