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

Dataset: The Pile

Neuron 1342 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: 1.1446. Min Range: -1.1446

Max Act: 1.1446. Min Act: -0.0000

Data Index: 179636 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.1020. Min Act: -0.0000

Data Index: 1568652 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.0928. Min Act: -0.0000

Data Index: 1190011 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.0254. Min Act: -0.0000

Data Index: 901287 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.0801. Min Act: -0.0000

Data Index: 762789 (The Pile)

Max Activating Token Index: 45

Text #5

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.0692. Min Act: -0.0000

Data Index: 319865 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.0536. Min Act: -0.0000

Data Index: 1760573 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.0094. Min Act: -0.0000

Data Index: 396811 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.0592. Min Act: -0.0000

Data Index: 291681 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1603398 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1798194 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1531949 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9663. Min Act: -0.0000

Data Index: 538038 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1286430 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9334. Min Act: -0.0000

Data Index: 281001 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8977. Min Act: -0.0000

Data Index: 883727 (The Pile)

Max Activating Token Index: 800

Text #16

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1608462 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1480559 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1387056 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9066. Min Act: -0.0000

Data Index: 986795 (The Pile)

Max Activating Token Index: 384