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

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

Neuron 2309 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: 0.1191. Min Range: -0.1191

Max Act: 0.1191. Min Act: -0.0000

Data Index: 275197 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1473537 (Python Code)

Max Activating Token Index: 997

Text #2

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0949. Min Act: -0.0000

Data Index: 863719 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0856. Min Act: -0.0000

Data Index: 871749 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0855. Min Act: -0.0000

Data Index: 279674 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0823. Min Act: -0.0000

Data Index: 848423 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1566202 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1171618 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0713. Min Act: -0.0000

Data Index: 1282278 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1521804 (Python Code)

Max Activating Token Index: 983

Text #10

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1009559 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1174544 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1561336 (Python Code)

Max Activating Token Index: 666

Text #13

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1214782 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1431849 (Python Code)

Max Activating Token Index: 689

Text #15

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0655. Min Act: -0.0000

Data Index: 845859 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0592. Min Act: -0.0000

Data Index: 621703 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0635. Min Act: -0.0000

Data Index: 478421 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1572058 (Python Code)

Max Activating Token Index: 492

Text #19

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0604. Min Act: -0.0000

Data Index: 503866 (C4 (Web Text))

Max Activating Token Index: 776