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

Dataset: The Pile

Neuron 1319 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0154. Min Range: -4.0154

Max Act: 4.0154. Min Act: -0.0000

Data Index: 201642 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6595. Min Act: -0.0000

Data Index: 1793976 (The Pile)

Max Activating Token Index: 702

Text #2

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6560. Min Act: -0.0000

Data Index: 823354 (The Pile)

Max Activating Token Index: 257

Text #3

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.4648. Min Act: -0.0000

Data Index: 1788423 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6388. Min Act: -0.0000

Data Index: 854013 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6459. Min Act: -0.0000

Data Index: 253517 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.3535. Min Act: -0.0000

Data Index: 1647759 (The Pile)

Max Activating Token Index: 655

Text #7

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.4523. Min Act: -0.0000

Data Index: 333734 (The Pile)

Max Activating Token Index: 410

Text #8

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.3347. Min Act: -0.0000

Data Index: 1016356 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.3195. Min Act: -0.0000

Data Index: 688363 (The Pile)

Max Activating Token Index: 451

Text #10

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.2866. Min Act: -0.0000

Data Index: 1333109 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.1396. Min Act: -0.0000

Data Index: 1570102 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 4.0154. Min Range: -4.0154

Max Act: 2.9972. Min Act: -0.0000

Data Index: 1146244 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.2716. Min Act: -0.0000

Data Index: 1423210 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.2582. Min Act: -0.0000

Data Index: 244819 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.2573. Min Act: -0.0000

Data Index: 370672 (The Pile)

Max Activating Token Index: 677

Text #16

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.1221. Min Act: -0.0000

Data Index: 1595319 (The Pile)

Max Activating Token Index: 612

Text #17

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.2286. Min Act: -0.0000

Data Index: 1916475 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.2468. Min Act: -0.0000

Data Index: 352076 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.2360. Min Act: -0.0000

Data Index: 1186977 (The Pile)

Max Activating Token Index: 1020