Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5135 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.9779. Min Act: -0.0000

Data Index: 39357 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 1.0590. Min Range: -1.0590

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1619725 (Python Code)

Max Activating Token Index: 332

Text #2

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1552240 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1347106 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.8028. Min Act: -0.0000

Data Index: 639823 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.8201. Min Act: -0.0000

Data Index: 140443 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.7489. Min Act: -0.0000

Data Index: 361795 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.7343. Min Act: -0.0000

Data Index: 275770 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1206768 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.7030. Min Act: -0.0000

Data Index: 260851 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1173824 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.8065. Min Act: -0.0000

Data Index: 845796 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.8022. Min Act: -0.0000

Data Index: 471709 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.7769. Min Act: -0.0000

Data Index: 56473 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.6743. Min Act: -0.0000

Data Index: 128570 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1529858 (Python Code)

Max Activating Token Index: 222

Text #16

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.6588. Min Act: -0.0000

Data Index: 1652800 (Python Code)

Max Activating Token Index: 306

Text #17

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.7334. Min Act: -0.0000

Data Index: 134825 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.7035. Min Act: -0.0000

Data Index: 841322 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 1.0590. Min Range: -1.0590

Max Act: 0.7505. Min Act: -0.0000

Data Index: 963303 (C4 (Web Text))

Max Activating Token Index: 484