Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2853 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.6710. Min Act: -0.0002

Data Index: 1463809 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.5719. Min Act: -0.0002

Data Index: 1438399 (Python Code)

Max Activating Token Index: 165

Text #2

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4807. Min Act: -0.0002

Data Index: 1509613 (Python Code)

Max Activating Token Index: 353

Text #3

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4294. Min Act: -0.0002

Data Index: 1419191 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4654. Min Act: -0.0002

Data Index: 1477657 (Python Code)

Max Activating Token Index: 511

Text #5

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4352. Min Act: -0.0002

Data Index: 1559048 (Python Code)

Max Activating Token Index: 299

Text #6

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4213. Min Act: -0.0002

Data Index: 1383186 (Python Code)

Max Activating Token Index: 57

Text #7

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4663. Min Act: -0.0002

Data Index: 1446428 (Python Code)

Max Activating Token Index: 474

Text #8

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.3791. Min Act: -0.0002

Data Index: 1533539 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1767. Min Act: -0.0002

Data Index: 1637732 (Python Code)

Max Activating Token Index: 534

Text #10

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.2912. Min Act: -0.0002

Data Index: 1579361 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.2892. Min Act: -0.0002

Data Index: 1514217 (Python Code)

Max Activating Token Index: 528

Text #12

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4123. Min Act: -0.0002

Data Index: 1429969 (Python Code)

Max Activating Token Index: 732

Text #13

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.2222. Min Act: -0.0002

Data Index: 1567518 (Python Code)

Max Activating Token Index: 553

Text #14

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.2255. Min Act: -0.0002

Data Index: 1384844 (Python Code)

Max Activating Token Index: 434

Text #15

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1816. Min Act: -0.0002

Data Index: 1438457 (Python Code)

Max Activating Token Index: 582

Text #16

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.3028. Min Act: -0.0002

Data Index: 1513466 (Python Code)

Max Activating Token Index: 917

Text #17

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.2226. Min Act: -0.0002

Data Index: 1593485 (Python Code)

Max Activating Token Index: 444

Text #18

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.2444. Min Act: -0.0002

Data Index: 1533826 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.2238. Min Act: -0.0002

Data Index: 1489299 (Python Code)

Max Activating Token Index: 49