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

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

Neuron 197 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7980. Min Act: -0.0001

Data Index: 330855 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7772. Min Act: -0.0000

Data Index: 176979 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7360. Min Act: -0.0000

Data Index: 231586 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7331. Min Act: -0.0001

Data Index: 180098 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7458. Min Act: -0.0000

Data Index: 117406 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1453197 (Python Code)

Max Activating Token Index: 827

Text #6

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7163. Min Act: -0.0001

Data Index: 787388 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6528. Min Act: -0.0000

Data Index: 725144 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6833. Min Act: -0.0001

Data Index: 143138 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7272. Min Act: -0.0000

Data Index: 491775 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7275. Min Act: -0.0001

Data Index: 155320 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7071. Min Act: -0.0001

Data Index: 282825 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7016. Min Act: -0.0000

Data Index: 77451 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7006. Min Act: -0.0001

Data Index: 992975 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1619927 (Python Code)

Max Activating Token Index: 427

Text #15

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7162. Min Act: -0.0001

Data Index: 327552 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6882. Min Act: -0.0001

Data Index: 354024 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6432. Min Act: -0.0001

Data Index: 1054152 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7360. Min Act: -0.0000

Data Index: 128659 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1600425 (Python Code)

Max Activating Token Index: 385