Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2986 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1396547 (Python Code)

Max Activating Token Index: 672

Text #1

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.4184. Min Act: -0.0000

Data Index: 759648 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1644229 (Python Code)

Max Activating Token Index: 1015

Text #3

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.2667. Min Act: -0.0000

Data Index: 962723 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.2406. Min Act: -0.0000

Data Index: 739894 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1401485 (Python Code)

Max Activating Token Index: 31

Text #6

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1738. Min Act: -0.0000

Data Index: 1578440 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1250432 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1011. Min Act: -0.0000

Data Index: 305863 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0680. Min Act: -0.0001

Data Index: 1496039 (Python Code)

Max Activating Token Index: 149

Text #10

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0607. Min Act: -0.0000

Data Index: 408091 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0449. Min Act: -0.0000

Data Index: 1439970 (Python Code)

Max Activating Token Index: 255

Text #12

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0507. Min Act: -0.0000

Data Index: 922879 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0660. Min Act: -0.0000

Data Index: 1416352 (Python Code)

Max Activating Token Index: 72

Text #14

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0636. Min Act: -0.0000

Data Index: 917916 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0943. Min Act: -0.0000

Data Index: 927358 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0492. Min Act: -0.0001

Data Index: 1205039 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.9845. Min Act: -0.0001

Data Index: 1029354 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.9746. Min Act: -0.0001

Data Index: 1495466 (Python Code)

Max Activating Token Index: 663

Text #19

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1252231 (C4 (Web Text))

Max Activating Token Index: 303