Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2889 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1948. Min Act: -0.0003

Data Index: 1009833 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1793. Min Act: -0.0003

Data Index: 1257674 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1705. Min Act: -0.0003

Data Index: 742783 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1675. Min Act: -0.0003

Data Index: 452093 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1800. Min Act: -0.0003

Data Index: 783320 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1581. Min Act: -0.0003

Data Index: 636209 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1565. Min Act: -0.0003

Data Index: 1596143 (Python Code)

Max Activating Token Index: 569

Text #7

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1825. Min Act: -0.0003

Data Index: 211902 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1626. Min Act: -0.0003

Data Index: 1077914 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1622. Min Act: -0.0003

Data Index: 510015 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1612. Min Act: -0.0003

Data Index: 346206 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1597. Min Act: -0.0003

Data Index: 488464 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1626. Min Act: -0.0003

Data Index: 356525 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1555. Min Act: -0.0003

Data Index: 539537 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1478. Min Act: -0.0003

Data Index: 109485 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1704. Min Act: -0.0003

Data Index: 1285181 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1485. Min Act: -0.0003

Data Index: 130555 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1525. Min Act: -0.0003

Data Index: 705617 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1527. Min Act: -0.0003

Data Index: 1383327 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1651. Min Act: -0.0003

Data Index: 183192 (C4 (Web Text))

Max Activating Token Index: 57