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

Dataset: The Pile

Neuron 196 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.4657. Min Act: -0.0000

Data Index: 805010 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.4889. Min Act: -0.0000

Data Index: 693740 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.2424. Min Act: -0.0000

Data Index: 1527550 (The Pile)

Max Activating Token Index: 673

Text #3

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.2471. Min Act: -0.0000

Data Index: 60890 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.2259. Min Act: -0.0000

Data Index: 1870109 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.2543. Min Act: -0.0000

Data Index: 1263445 (The Pile)

Max Activating Token Index: 400

Text #6

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1116433 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.1331. Min Act: -0.0000

Data Index: 1125014 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.0671. Min Act: -0.0000

Data Index: 304316 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1471345 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.0789. Min Act: -0.0000

Data Index: 1932592 (The Pile)

Max Activating Token Index: 795

Text #11

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.0637. Min Act: -0.0000

Data Index: 836473 (The Pile)

Max Activating Token Index: 823

Text #12

Max Range: 1.4889. Min Range: -1.4889

Max Act: 1.1768. Min Act: -0.0000

Data Index: 601803 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 1.4889. Min Range: -1.4889

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1381339 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 1.4889. Min Range: -1.4889

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1103531 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 1.4889. Min Range: -1.4889

Max Act: 0.9658. Min Act: -0.0000

Data Index: 376589 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 1.4889. Min Range: -1.4889

Max Act: 0.9954. Min Act: -0.0000

Data Index: 256082 (The Pile)

Max Activating Token Index: 302

Text #17

Max Range: 1.4889. Min Range: -1.4889

Max Act: 0.9183. Min Act: 0.0000

Data Index: 1170438 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 1.4889. Min Range: -1.4889

Max Act: 0.8995. Min Act: -0.0000

Data Index: 317236 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 1.4889. Min Range: -1.4889

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1014632 (The Pile)

Max Activating Token Index: 353