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

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

Neuron 1582 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.5013. Min Act: -0.0001

Data Index: 1238975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1559380 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.2713. Min Act: -0.0001

Data Index: 1003149 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3208. Min Act: -0.0001

Data Index: 1264794 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.1955. Min Act: -0.0001

Data Index: 27857 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.1031. Min Act: -0.0001

Data Index: 389487 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1252141 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.2448. Min Act: -0.0001

Data Index: 505329 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.2357. Min Act: -0.0001

Data Index: 64443 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.1542. Min Act: -0.0001

Data Index: 36179 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.2398. Min Act: -0.0001

Data Index: 1003105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.1005. Min Act: -0.0001

Data Index: 203201 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.2034. Min Act: -0.0001

Data Index: 1408611 (Python Code)

Max Activating Token Index: 917

Text #13

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1475822 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1393477 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1452875 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.0982. Min Act: -0.0001

Data Index: 539721 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.1903. Min Act: -0.0001

Data Index: 843429 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1605502 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1477651 (Python Code)

Max Activating Token Index: 1023