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

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

Neuron 3941 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2639. Min Act: -0.0000

Data Index: 134204 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2417. Min Act: -0.0000

Data Index: 37592 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2209. Min Act: -0.0000

Data Index: 247918 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1206089 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2183. Min Act: -0.0000

Data Index: 516741 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2024. Min Act: -0.0000

Data Index: 705499 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1868. Min Act: -0.0000

Data Index: 390530 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1975. Min Act: -0.0000

Data Index: 449725 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1085005 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1319328 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1714. Min Act: -0.0000

Data Index: 914356 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1699. Min Act: 0.0000

Data Index: 203734 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1120310 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1334058 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1582. Min Act: -0.0000

Data Index: 890516 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1177933 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1484. Min Act: -0.0000

Data Index: 246488 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1290497 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1528. Min Act: -0.0000

Data Index: 644657 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1450. Min Act: -0.0000

Data Index: 972519 (C4 (Web Text))

Max Activating Token Index: 441