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

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

Neuron 1749 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4297. Min Range: -3.4297

Max Act: 3.4297. Min Act: -0.0000

Data Index: 1384714 (Python Code)

Max Activating Token Index: 252

Text #1

Max Range: 3.4297. Min Range: -3.4297

Max Act: 3.0795. Min Act: -0.0000

Data Index: 1615623 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.9917. Min Act: -0.0000

Data Index: 1595426 (Python Code)

Max Activating Token Index: 90

Text #3

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.8659. Min Act: -0.0000

Data Index: 1649509 (Python Code)

Max Activating Token Index: 28

Text #4

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.5933. Min Act: -0.0000

Data Index: 1632216 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.5627. Min Act: -0.0000

Data Index: 1412423 (Python Code)

Max Activating Token Index: 270

Text #6

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.1563. Min Act: -0.0000

Data Index: 1621857 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.1432. Min Act: -0.0000

Data Index: 1648162 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.1929. Min Act: -0.0000

Data Index: 1609288 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.2071. Min Act: -0.0000

Data Index: 1542020 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.1623. Min Act: -0.0000

Data Index: 1593812 (Python Code)

Max Activating Token Index: 325

Text #11

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.1140. Min Act: -0.0000

Data Index: 1470634 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.0979. Min Act: -0.0000

Data Index: 1468660 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.8133. Min Act: -0.0000

Data Index: 1378478 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.7215. Min Act: -0.0000

Data Index: 1507313 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.7797. Min Act: -0.0000

Data Index: 1418794 (Python Code)

Max Activating Token Index: 286

Text #16

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.8733. Min Act: -0.0000

Data Index: 1563465 (Python Code)

Max Activating Token Index: 286

Text #17

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.6686. Min Act: -0.0000

Data Index: 1528780 (Python Code)

Max Activating Token Index: 431

Text #18

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.7398. Min Act: -0.0000

Data Index: 1635713 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.7309. Min Act: -0.0000

Data Index: 1403566 (Python Code)

Max Activating Token Index: 379