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

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

Neuron 2977 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1531545 (Python Code)

Max Activating Token Index: 755

Text #1

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1495788 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2291. Min Act: -0.0001

Data Index: 1493937 (Python Code)

Max Activating Token Index: 967

Text #3

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1339206 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1341871 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1742. Min Act: -0.0000

Data Index: 284134 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1204643 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1102136 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1974. Min Act: -0.0000

Data Index: 587182 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1297244 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1616361 (Python Code)

Max Activating Token Index: 646

Text #11

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1898. Min Act: -0.0000

Data Index: 817906 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1463511 (Python Code)

Max Activating Token Index: 295

Text #13

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1745. Min Act: -0.0000

Data Index: 538471 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1954. Min Act: -0.0001

Data Index: 1586212 (Python Code)

Max Activating Token Index: 706

Text #15

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1035180 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1747. Min Act: -0.0000

Data Index: 239328 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1110752 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1209707 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1340082 (C4 (Web Text))

Max Activating Token Index: 691