Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1572 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5334. Min Act: -0.0001

Data Index: 463746 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.3926. Min Act: -0.0001

Data Index: 979915 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.3278. Min Act: -0.0001

Data Index: 238194 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.2479. Min Act: -0.0001

Data Index: 1257422 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.3381. Min Act: -0.0001

Data Index: 1192844 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.2213. Min Act: -0.0001

Data Index: 820808 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.0629. Min Act: -0.0001

Data Index: 331852 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1067. Min Act: -0.0001

Data Index: 1357628 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1776. Min Act: -0.0001

Data Index: 138876 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.0619. Min Act: -0.0001

Data Index: 95367 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1023. Min Act: -0.0001

Data Index: 1115516 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 1.5334. Min Range: -1.5334

Max Act: 0.9990. Min Act: -0.0001

Data Index: 167622 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.0849. Min Act: -0.0001

Data Index: 409937 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 1.5334. Min Range: -1.5334

Max Act: 0.9789. Min Act: -0.0001

Data Index: 775171 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 1.5334. Min Range: -1.5334

Max Act: 0.9753. Min Act: -0.0001

Data Index: 508146 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 1.5334. Min Range: -1.5334

Max Act: 0.9746. Min Act: -0.0001

Data Index: 1186033 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 1.5334. Min Range: -1.5334

Max Act: 0.9988. Min Act: -0.0001

Data Index: 786309 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.5334. Min Range: -1.5334

Max Act: 0.9888. Min Act: -0.0001

Data Index: 881037 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 1.5334. Min Range: -1.5334

Max Act: 0.9944. Min Act: -0.0001

Data Index: 289149 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.5334. Min Range: -1.5334

Max Act: 0.9362. Min Act: -0.0001

Data Index: 78507 (C4 (Web Text))

Max Activating Token Index: 985