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

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

Neuron 6068 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0900. Min Act: -0.0002

Data Index: 349559 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0786. Min Act: -0.0002

Data Index: 37456 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1296248 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1232030 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0701. Min Act: -0.0002

Data Index: 973401 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0693. Min Act: -0.0002

Data Index: 225276 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0742. Min Act: -0.0002

Data Index: 454229 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0700. Min Act: -0.0002

Data Index: 917981 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0689. Min Act: -0.0002

Data Index: 780260 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0685. Min Act: -0.0002

Data Index: 984927 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1289964 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0654. Min Act: -0.0002

Data Index: 860150 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0653. Min Act: -0.0002

Data Index: 220483 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0620. Min Act: -0.0002

Data Index: 414617 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1141259 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0665. Min Act: -0.0002

Data Index: 780863 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0627. Min Act: -0.0002

Data Index: 121161 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0610. Min Act: -0.0002

Data Index: 16942 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0631. Min Act: -0.0002

Data Index: 597340 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0610. Min Act: -0.0002

Data Index: 565179 (C4 (Web Text))

Max Activating Token Index: 130