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

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

Neuron 2358 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1143636 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0757. Min Act: -0.0002

Data Index: 945707 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1154718 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0702. Min Act: -0.0003

Data Index: 81526 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0704. Min Act: -0.0002

Data Index: 755012 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0683. Min Act: -0.0002

Data Index: 932019 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0684. Min Act: -0.0003

Data Index: 20559 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0666. Min Act: -0.0002

Data Index: 104111 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0642. Min Act: -0.0002

Data Index: 139409 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0635. Min Act: -0.0002

Data Index: 253227 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1350233 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0622. Min Act: -0.0002

Data Index: 460509 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0612. Min Act: -0.0002

Data Index: 958146 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1234929 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0613. Min Act: -0.0002

Data Index: 159744 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0603. Min Act: -0.0002

Data Index: 750996 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0584. Min Act: -0.0002

Data Index: 380304 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1231327 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0578. Min Act: -0.0002

Data Index: 428970 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0568. Min Act: -0.0002

Data Index: 6062 (C4 (Web Text))

Max Activating Token Index: 70