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

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

Neuron 3502 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1062060 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.8877. Min Act: -0.0000

Data Index: 615812 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.8003. Min Act: -0.0000

Data Index: 461631 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.8131. Min Act: -0.0000

Data Index: 6417 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1186959 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1289612 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7522. Min Act: -0.0000

Data Index: 870394 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1347369 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7478. Min Act: -0.0000

Data Index: 163724 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6848. Min Act: -0.0000

Data Index: 794297 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7494. Min Act: -0.0000

Data Index: 592143 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7291. Min Act: -0.0000

Data Index: 821816 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1297129 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6834. Min Act: -0.0000

Data Index: 674885 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1062297 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7141. Min Act: -0.0000

Data Index: 150572 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1358077 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7189. Min Act: -0.0000

Data Index: 485797 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1235157 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6942. Min Act: -0.0000

Data Index: 852456 (C4 (Web Text))

Max Activating Token Index: 359