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

Dataset: The Pile

Neuron 3910 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1401213 (The Pile)

Max Activating Token Index: 632

Text #1

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0660. Min Act: -0.0000

Data Index: 623576 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0671. Min Act: -0.0000

Data Index: 233886 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1227988 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0592. Min Act: -0.0000

Data Index: 380876 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1337157 (The Pile)

Max Activating Token Index: 728

Text #6

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0606. Min Act: -0.0000

Data Index: 608171 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0622. Min Act: -0.0000

Data Index: 750427 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1124706 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1725575 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1761142 (The Pile)

Max Activating Token Index: 329

Text #11

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0610. Min Act: -0.0000

Data Index: 448670 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1330595 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1023208 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1564380 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0547. Min Act: -0.0000

Data Index: 187356 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1254063 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1123754 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1397049 (The Pile)

Max Activating Token Index: 707

Text #19

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0592. Min Act: -0.0000

Data Index: 506364 (The Pile)

Max Activating Token Index: 707