Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 544 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.5421. Min Act: -0.0001

Data Index: 1423986 (Python Code)

Max Activating Token Index: 375

Text #1

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.5209. Min Act: -0.0001

Data Index: 1516687 (Python Code)

Max Activating Token Index: 360

Text #2

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4746. Min Act: -0.0001

Data Index: 1466189 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4811. Min Act: -0.0001

Data Index: 1588631 (Python Code)

Max Activating Token Index: 313

Text #4

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4736. Min Act: -0.0001

Data Index: 1640813 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3937. Min Act: -0.0001

Data Index: 783916 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4139. Min Act: -0.0001

Data Index: 400251 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4359. Min Act: -0.0001

Data Index: 1585928 (Python Code)

Max Activating Token Index: 732

Text #8

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3798. Min Act: -0.0001

Data Index: 1354664 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3726. Min Act: -0.0001

Data Index: 844253 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3894. Min Act: -0.0001

Data Index: 1561106 (Python Code)

Max Activating Token Index: 549

Text #11

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3556. Min Act: -0.0001

Data Index: 455666 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3815. Min Act: -0.0001

Data Index: 687172 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3482. Min Act: -0.0001

Data Index: 603663 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3933. Min Act: -0.0001

Data Index: 549534 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3719. Min Act: -0.0001

Data Index: 583036 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4272. Min Act: -0.0001

Data Index: 1166070 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3747. Min Act: -0.0001

Data Index: 1544180 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3469. Min Act: -0.0001

Data Index: 1265181 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3468. Min Act: -0.0001

Data Index: 720603 (C4 (Web Text))

Max Activating Token Index: 175