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

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

Neuron 3692 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1675. Min Range: -1.1675

Max Act: 1.0873. Min Act: -0.0001

Data Index: 1591486 (Python Code)

Max Activating Token Index: 269

Text #1

Max Range: 1.1675. Min Range: -1.1675

Max Act: 1.1675. Min Act: -0.0002

Data Index: 827647 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 1.1675. Min Range: -1.1675

Max Act: 1.0472. Min Act: -0.0001

Data Index: 1492752 (Python Code)

Max Activating Token Index: 850

Text #3

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.9417. Min Act: -0.0001

Data Index: 1464934 (Python Code)

Max Activating Token Index: 54

Text #4

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.9010. Min Act: -0.0001

Data Index: 1563749 (Python Code)

Max Activating Token Index: 748

Text #5

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.8984. Min Act: -0.0001

Data Index: 1390865 (Python Code)

Max Activating Token Index: 336

Text #6

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.8960. Min Act: -0.0002

Data Index: 1256157 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.9202. Min Act: -0.0001

Data Index: 1454591 (Python Code)

Max Activating Token Index: 271

Text #8

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.9380. Min Act: -0.0001

Data Index: 1493790 (Python Code)

Max Activating Token Index: 199

Text #9

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.9527. Min Act: -0.0001

Data Index: 1562692 (Python Code)

Max Activating Token Index: 524

Text #10

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.9204. Min Act: -0.0001

Data Index: 1389126 (Python Code)

Max Activating Token Index: 776

Text #11

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.8657. Min Act: -0.0001

Data Index: 1360933 (Python Code)

Max Activating Token Index: 972

Text #12

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.8886. Min Act: -0.0001

Data Index: 1404551 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.8842. Min Act: -0.0002

Data Index: 755687 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.8540. Min Act: -0.0002

Data Index: 421544 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.8644. Min Act: -0.0001

Data Index: 1542300 (Python Code)

Max Activating Token Index: 624

Text #16

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.8408. Min Act: -0.0001

Data Index: 1414267 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.8426. Min Act: -0.0001

Data Index: 1579130 (Python Code)

Max Activating Token Index: 143

Text #18

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.8320. Min Act: -0.0001

Data Index: 1607474 (Python Code)

Max Activating Token Index: 46

Text #19

Max Range: 1.1675. Min Range: -1.1675

Max Act: 0.8001. Min Act: -0.0001

Data Index: 1457941 (Python Code)

Max Activating Token Index: 238