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

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

Neuron 5176 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.1000. Min Act: -0.0000

Data Index: 98027 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0855. Min Act: -0.0000

Data Index: 20351 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0802. Min Act: -0.0000

Data Index: 873351 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1539724 (Python Code)

Max Activating Token Index: 104

Text #4

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0776. Min Act: -0.0000

Data Index: 851466 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0777. Min Act: -0.0000

Data Index: 896096 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0770. Min Act: -0.0000

Data Index: 256252 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0732. Min Act: -0.0000

Data Index: 724525 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0707. Min Act: -0.0000

Data Index: 3138 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0739. Min Act: -0.0000

Data Index: 1100948 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1173456 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0688. Min Act: -0.0000

Data Index: 981021 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0684. Min Act: 0.0000

Data Index: 999653 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1605087 (Python Code)

Max Activating Token Index: 1007

Text #14

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1505349 (Python Code)

Max Activating Token Index: 472

Text #15

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0679. Min Act: -0.0000

Data Index: 304890 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1521676 (Python Code)

Max Activating Token Index: 24

Text #17

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0629. Min Act: -0.0000

Data Index: 863618 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0627. Min Act: -0.0000

Data Index: 135221 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0626. Min Act: -0.0000

Data Index: 438263 (C4 (Web Text))

Max Activating Token Index: 195