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

Dataset: The Pile

Neuron 2424 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1739872 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2750. Min Act: -0.0000

Data Index: 801581 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1503333 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2466. Min Act: -0.0000

Data Index: 978628 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1661982 (The Pile)

Max Activating Token Index: 377

Text #5

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2634. Min Act: -0.0000

Data Index: 689832 (The Pile)

Max Activating Token Index: 941

Text #6

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1648896 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1799003 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2738. Min Act: -0.0000

Data Index: 65866 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1153207 (The Pile)

Max Activating Token Index: 204

Text #10

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1672464 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2386. Min Act: -0.0000

Data Index: 201432 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1974791 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1373480 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1484397 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2347. Min Act: -0.0000

Data Index: 335259 (The Pile)

Max Activating Token Index: 418

Text #16

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1462483 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2078. Min Act: -0.0000

Data Index: 96638 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2065. Min Act: -0.0000

Data Index: 812352 (The Pile)

Max Activating Token Index: 352

Text #19

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1618872 (The Pile)

Max Activating Token Index: 671