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

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

Neuron 1003 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1372538 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4821. Min Act: -0.0000

Data Index: 392150 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1402457 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1453746 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4150. Min Act: -0.0001

Data Index: 1240085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1521772 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4475. Min Act: -0.0000

Data Index: 193111 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4236. Min Act: -0.0000

Data Index: 875521 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3449. Min Act: -0.0000

Data Index: 1454652 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1441577 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1455982 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3607. Min Act: -0.0001

Data Index: 178126 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1650772 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1365432 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1291343 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1222165 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3431. Min Act: -0.0001

Data Index: 374958 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3680. Min Act: -0.0001

Data Index: 185091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1561362 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3856. Min Act: -0.0000

Data Index: 250950 (C4 (Web Text))

Max Activating Token Index: 1023