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

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

Neuron 1767 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2362. Min Act: -0.0002

Data Index: 449798 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2116. Min Act: -0.0002

Data Index: 1315653 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2026. Min Act: -0.0002

Data Index: 1130356 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1974. Min Act: -0.0002

Data Index: 1183787 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1869. Min Act: -0.0002

Data Index: 1220410 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1912. Min Act: -0.0002

Data Index: 627494 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1906. Min Act: -0.0002

Data Index: 1092116 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1827. Min Act: -0.0002

Data Index: 835499 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1792. Min Act: -0.0002

Data Index: 52193 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1772. Min Act: -0.0002

Data Index: 1182747 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1726. Min Act: -0.0002

Data Index: 17741 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1727. Min Act: -0.0002

Data Index: 1209843 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1694. Min Act: -0.0002

Data Index: 48030 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1675. Min Act: -0.0002

Data Index: 1247127 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1643. Min Act: -0.0002

Data Index: 74492 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1635. Min Act: -0.0002

Data Index: 77426 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1623. Min Act: -0.0002

Data Index: 418442 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1676. Min Act: -0.0002

Data Index: 483105 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1552. Min Act: -0.0002

Data Index: 1325665 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1550. Min Act: -0.0002

Data Index: 756436 (C4 (Web Text))

Max Activating Token Index: 337