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

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

Neuron 1779 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: 4.5734. Min Range: -4.5734

Max Act: 4.5734. Min Act: -0.0000

Data Index: 1317250 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 4.5734. Min Range: -4.5734

Max Act: 4.1988. Min Act: -0.0000

Data Index: 1307857 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 4.5734. Min Range: -4.5734

Max Act: 4.3600. Min Act: -0.0001

Data Index: 1294305 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 4.5734. Min Range: -4.5734

Max Act: 4.0143. Min Act: -0.0000

Data Index: 947423 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.9415. Min Act: -0.0000

Data Index: 1357366 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 4.5734. Min Range: -4.5734

Max Act: 4.0453. Min Act: -0.0000

Data Index: 493778 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.8032. Min Act: -0.0000

Data Index: 1015987 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.7397. Min Act: -0.0001

Data Index: 886532 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.6857. Min Act: -0.0001

Data Index: 1460374 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.4990. Min Act: -0.0001

Data Index: 1213354 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.6149. Min Act: -0.0001

Data Index: 754305 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.7972. Min Act: -0.0001

Data Index: 301032 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.3387. Min Act: -0.0001

Data Index: 1457552 (Python Code)

Max Activating Token Index: 518

Text #13

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.5117. Min Act: -0.0001

Data Index: 465957 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.2251. Min Act: -0.0001

Data Index: 540994 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.5195. Min Act: -0.0001

Data Index: 1576823 (Python Code)

Max Activating Token Index: 427

Text #16

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.3322. Min Act: -0.0001

Data Index: 1276430 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.4681. Min Act: -0.0001

Data Index: 1197223 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.2973. Min Act: -0.0001

Data Index: 1325641 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 4.5734. Min Range: -4.5734

Max Act: 3.2629. Min Act: -0.0001

Data Index: 635388 (C4 (Web Text))

Max Activating Token Index: 474