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

Dataset: The Pile

Neuron 2547 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: 1.0703. Min Range: -1.0703

Max Act: 0.9867. Min Act: -0.0000

Data Index: 776418 (The Pile)

Max Activating Token Index: 302

Text #1

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1639203 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 1.0703. Min Range: -1.0703

Max Act: 1.0703. Min Act: -0.0000

Data Index: 464985 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.9055. Min Act: -0.0000

Data Index: 259071 (The Pile)

Max Activating Token Index: 945

Text #4

Max Range: 1.0703. Min Range: -1.0703

Max Act: 1.0281. Min Act: -0.0000

Data Index: 163913 (The Pile)

Max Activating Token Index: 964

Text #5

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7498. Min Act: -0.0000

Data Index: 932734 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1131186 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.8282. Min Act: -0.0000

Data Index: 913135 (The Pile)

Max Activating Token Index: 659

Text #8

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1865747 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7610. Min Act: -0.0000

Data Index: 741099 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7746. Min Act: -0.0000

Data Index: 88873 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7003. Min Act: -0.0000

Data Index: 368190 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7225. Min Act: -0.0000

Data Index: 1385748 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7100. Min Act: -0.0000

Data Index: 753939 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6656. Min Act: -0.0000

Data Index: 239909 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6885. Min Act: -0.0000

Data Index: 360547 (The Pile)

Max Activating Token Index: 678

Text #16

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1923404 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7310. Min Act: -0.0000

Data Index: 362340 (The Pile)

Max Activating Token Index: 925

Text #18

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6676. Min Act: -0.0000

Data Index: 82284 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1492739 (The Pile)

Max Activating Token Index: 716