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

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

Neuron 1982 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1016. Min Range: -4.1016

Max Act: 4.1016. Min Act: -0.0001

Data Index: 1542190 (Python Code)

Max Activating Token Index: 911

Text #1

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.4815. Min Act: -0.0001

Data Index: 1623096 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.4128. Min Act: -0.0001

Data Index: 1425985 (Python Code)

Max Activating Token Index: 502

Text #3

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.2089. Min Act: -0.0000

Data Index: 1332996 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.1653. Min Act: -0.0001

Data Index: 1530968 (Python Code)

Max Activating Token Index: 1013

Text #5

Max Range: 4.1016. Min Range: -4.1016

Max Act: 2.8189. Min Act: -0.0001

Data Index: 1396898 (Python Code)

Max Activating Token Index: 554

Text #6

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.0792. Min Act: -0.0001

Data Index: 1517274 (Python Code)

Max Activating Token Index: 997

Text #7

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.0225. Min Act: -0.0001

Data Index: 1455425 (Python Code)

Max Activating Token Index: 628

Text #8

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.1135. Min Act: -0.0001

Data Index: 1563869 (Python Code)

Max Activating Token Index: 533

Text #9

Max Range: 4.1016. Min Range: -4.1016

Max Act: 2.6657. Min Act: -0.0001

Data Index: 1555984 (Python Code)

Max Activating Token Index: 917

Text #10

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.0723. Min Act: -0.0000

Data Index: 1181220 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 4.1016. Min Range: -4.1016

Max Act: 2.7067. Min Act: -0.0001

Data Index: 1534966 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 4.1016. Min Range: -4.1016

Max Act: 2.9581. Min Act: -0.0001

Data Index: 1374361 (Python Code)

Max Activating Token Index: 1019

Text #13

Max Range: 4.1016. Min Range: -4.1016

Max Act: 2.8512. Min Act: -0.0001

Data Index: 1383379 (Python Code)

Max Activating Token Index: 1014

Text #14

Max Range: 4.1016. Min Range: -4.1016

Max Act: 2.8299. Min Act: -0.0000

Data Index: 1630389 (Python Code)

Max Activating Token Index: 946

Text #15

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.0925. Min Act: -0.0001

Data Index: 52952 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 4.1016. Min Range: -4.1016

Max Act: 2.6962. Min Act: -0.0001

Data Index: 251476 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 4.1016. Min Range: -4.1016

Max Act: 2.9527. Min Act: -0.0001

Data Index: 1536153 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.0744. Min Act: -0.0001

Data Index: 1407979 (Python Code)

Max Activating Token Index: 1002

Text #19

Max Range: 4.1016. Min Range: -4.1016

Max Act: 2.9410. Min Act: -0.0000

Data Index: 88904 (C4 (Web Text))

Max Activating Token Index: 20