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

Dataset: The Pile

Neuron 592 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: 0.2349. Min Range: -0.2349

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1415578 (The Pile)

Max Activating Token Index: 533

Text #1

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.2206. Min Act: -0.0000

Data Index: 257488 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1115676 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1357702 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1772. Min Act: -0.0000

Data Index: 518242 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1999. Min Act: -0.0000

Data Index: 295869 (The Pile)

Max Activating Token Index: 635

Text #6

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1879. Min Act: -0.0000

Data Index: 1597645 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1417065 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1873263 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1762. Min Act: -0.0000

Data Index: 265888 (The Pile)

Max Activating Token Index: 305

Text #10

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1749. Min Act: -0.0000

Data Index: 1574581 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1311997 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1538429 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1894074 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1557. Min Act: -0.0000

Data Index: 599730 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1431571 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1068527 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1745980 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1712. Min Act: -0.0000

Data Index: 717228 (The Pile)

Max Activating Token Index: 270

Text #19

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1641198 (The Pile)

Max Activating Token Index: 316