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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 555 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1930. Min Act: -0.0001

Data Index: 602429 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1834. Min Act: -0.0001

Data Index: 243864 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1746. Min Act: -0.0001

Data Index: 370704 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1672. Min Act: -0.0001

Data Index: 50228 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1733. Min Act: -0.0001

Data Index: 632026 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1745. Min Act: -0.0001

Data Index: 108852 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1586. Min Act: -0.0001

Data Index: 308437 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1620. Min Act: -0.0001

Data Index: 405137 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1682. Min Act: -0.0001

Data Index: 965507 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1663. Min Act: -0.0001

Data Index: 473305 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1602. Min Act: -0.0001

Data Index: 677564 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1604. Min Act: -0.0001

Data Index: 204607 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1533. Min Act: -0.0001

Data Index: 504989 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1260650 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1649. Min Act: -0.0001

Data Index: 900130 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1136387 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1574. Min Act: -0.0001

Data Index: 313768 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1558. Min Act: -0.0001

Data Index: 836326 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1633. Min Act: -0.0001

Data Index: 903294 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1560. Min Act: -0.0001

Data Index: 414741 (C4 (Web Text))

Max Activating Token Index: 849