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

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

Neuron 2572 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: 0.2508. Min Range: -0.2508

Max Act: 0.2508. Min Act: -0.0001

Data Index: 281568 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2396. Min Act: -0.0001

Data Index: 483629 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2321. Min Act: -0.0001

Data Index: 865333 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2147. Min Act: -0.0001

Data Index: 808902 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2104. Min Act: -0.0001

Data Index: 1038446 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2214. Min Act: -0.0001

Data Index: 1329457 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1917. Min Act: -0.0001

Data Index: 732104 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1959. Min Act: -0.0001

Data Index: 1132244 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1838. Min Act: -0.0001

Data Index: 916285 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2064. Min Act: -0.0001

Data Index: 404009 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1895. Min Act: -0.0001

Data Index: 269362 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1923. Min Act: -0.0001

Data Index: 14399 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2031. Min Act: -0.0001

Data Index: 1207260 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1721. Min Act: -0.0001

Data Index: 880707 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1321342 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1854. Min Act: -0.0001

Data Index: 1204684 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1862. Min Act: -0.0001

Data Index: 824643 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1918. Min Act: -0.0001

Data Index: 31881 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1835. Min Act: -0.0001

Data Index: 395977 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1895. Min Act: -0.0001

Data Index: 910010 (C4 (Web Text))

Max Activating Token Index: 689