Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1525 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.9550. Min Act: -0.0001

Data Index: 761854 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 2.0077. Min Range: -2.0077

Max Act: 2.0077. Min Act: -0.0001

Data Index: 1349173 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.9007. Min Act: -0.0001

Data Index: 387983 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.9638. Min Act: -0.0000

Data Index: 1197828 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.8837. Min Act: -0.0001

Data Index: 571055 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.7533. Min Act: -0.0001

Data Index: 451997 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4101. Min Act: -0.0001

Data Index: 790699 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.7193. Min Act: -0.0001

Data Index: 1313152 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.5948. Min Act: -0.0001

Data Index: 908233 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.5695. Min Act: -0.0001

Data Index: 405614 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4084. Min Act: -0.0001

Data Index: 759807 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.7428. Min Act: -0.0001

Data Index: 25291 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.7189. Min Act: -0.0001

Data Index: 531512 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.5982. Min Act: -0.0001

Data Index: 490334 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.5856. Min Act: -0.0001

Data Index: 777252 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.7141. Min Act: -0.0001

Data Index: 967312 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.5651. Min Act: -0.0001

Data Index: 415935 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.5657. Min Act: -0.0001

Data Index: 1052813 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.6392. Min Act: -0.0000

Data Index: 1641388 (Python Code)

Max Activating Token Index: 874

Text #19

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.5421. Min Act: -0.0001

Data Index: 960929 (C4 (Web Text))

Max Activating Token Index: 6