Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 41 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.9195. Min Act: -0.0003

Data Index: 1416223 (Python Code)

Max Activating Token Index: 749

Text #1

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.3654. Min Act: -0.0003

Data Index: 1021418 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.2086. Min Act: -0.0004

Data Index: 1193413 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.2158. Min Act: -0.0003

Data Index: 229670 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1823. Min Act: -0.0003

Data Index: 20325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1779. Min Act: -0.0003

Data Index: 1179980 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1701. Min Act: -0.0003

Data Index: 317597 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1691. Min Act: -0.0003

Data Index: 580283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1724. Min Act: -0.0003

Data Index: 61472 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1712. Min Act: -0.0003

Data Index: 860375 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1708. Min Act: -0.0002

Data Index: 583473 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1707. Min Act: -0.0003

Data Index: 1221689 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1683. Min Act: -0.0003

Data Index: 272113 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1695. Min Act: -0.0003

Data Index: 702827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1693. Min Act: -0.0003

Data Index: 1044672 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1674. Min Act: -0.0003

Data Index: 991572 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1685. Min Act: -0.0003

Data Index: 1293414 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1696. Min Act: -0.0003

Data Index: 947907 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1687. Min Act: -0.0003

Data Index: 84495 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1677. Min Act: -0.0003

Data Index: 545503 (C4 (Web Text))

Max Activating Token Index: 1023