Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 186 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0899. Min Act: -0.0001

Data Index: 147068 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1467243 (Python Code)

Max Activating Token Index: 78

Text #2

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0640. Min Act: -0.0000

Data Index: 887532 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0655. Min Act: -0.0001

Data Index: 653167 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0620. Min Act: -0.0001

Data Index: 375697 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0613. Min Act: -0.0001

Data Index: 975333 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1049490 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0657. Min Act: -0.0001

Data Index: 742089 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1158832 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1216581 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0576. Min Act: -0.0000

Data Index: 472876 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1097740 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0572. Min Act: -0.0001

Data Index: 66678 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1343500 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1168315 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1193947 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0522. Min Act: -0.0001

Data Index: 955918 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0631. Min Act: -0.0001

Data Index: 980659 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0516. Min Act: -0.0001

Data Index: 773530 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1541362 (Python Code)

Max Activating Token Index: 437