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

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

Neuron 176 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: 0.2471. Min Range: -0.2471

Max Act: 0.2471. Min Act: 0.0000

Data Index: 501438 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.2235. Min Act: -0.0000

Data Index: 814338 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1040471 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.2101. Min Act: -0.0000

Data Index: 594420 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1115234 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1870. Min Act: -0.0000

Data Index: 590856 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1177700 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.2049. Min Act: -0.0000

Data Index: 450536 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1919. Min Act: -0.0000

Data Index: 893322 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1044656 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1895. Min Act: 0.0000

Data Index: 493429 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1025162 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1740. Min Act: -0.0000

Data Index: 804652 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1756. Min Act: -0.0000

Data Index: 887746 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1772. Min Act: -0.0000

Data Index: 520587 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1637. Min Act: -0.0000

Data Index: 473706 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1735. Min Act: -0.0000

Data Index: 15391 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1737. Min Act: -0.0000

Data Index: 698974 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1342723 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1732. Min Act: -0.0000

Data Index: 562431 (C4 (Web Text))

Max Activating Token Index: 487