Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4988 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1585. Min Act: -0.0001

Data Index: 22854 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1001340 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1031302 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1531. Min Act: -0.0001

Data Index: 816756 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1271. Min Act: -0.0001

Data Index: 696094 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1598. Min Act: -0.0001

Data Index: 652822 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1224097 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1320. Min Act: -0.0001

Data Index: 398234 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1304588 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1369. Min Act: -0.0001

Data Index: 396545 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1407. Min Act: -0.0001

Data Index: 616684 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1201. Min Act: -0.0001

Data Index: 930938 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1243. Min Act: -0.0001

Data Index: 52064 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1295736 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1300. Min Act: -0.0001

Data Index: 653611 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1257725 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1292186 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1265. Min Act: -0.0001

Data Index: 770826 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1266. Min Act: -0.0001

Data Index: 410019 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1137. Min Act: -0.0001

Data Index: 396305 (C4 (Web Text))

Max Activating Token Index: 72