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

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

Neuron 4231 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0706. Min Range: -1.0706

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1560544 (Python Code)

Max Activating Token Index: 359

Text #1

Max Range: 1.0706. Min Range: -1.0706

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1655473 (Python Code)

Max Activating Token Index: 957

Text #2

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9894. Min Act: -0.0000

Data Index: 1460334 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 1.0706. Min Range: -1.0706

Max Act: 1.0001. Min Act: 0.0000

Data Index: 1557506 (Python Code)

Max Activating Token Index: 726

Text #4

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1481944 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1592415 (Python Code)

Max Activating Token Index: 851

Text #6

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9802. Min Act: 0.0001

Data Index: 1471922 (Python Code)

Max Activating Token Index: 437

Text #7

Max Range: 1.0706. Min Range: -1.0706

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1393372 (Python Code)

Max Activating Token Index: 715

Text #8

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9086. Min Act: 0.0000

Data Index: 1599655 (Python Code)

Max Activating Token Index: 1009

Text #9

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1627366 (Python Code)

Max Activating Token Index: 594

Text #10

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9946. Min Act: -0.0000

Data Index: 1424392 (Python Code)

Max Activating Token Index: 958

Text #11

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9565. Min Act: 0.0000

Data Index: 1433179 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1452147 (Python Code)

Max Activating Token Index: 464

Text #13

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1505536 (Python Code)

Max Activating Token Index: 207

Text #14

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1468724 (Python Code)

Max Activating Token Index: 685

Text #15

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1506710 (Python Code)

Max Activating Token Index: 878

Text #16

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1417513 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1558316 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.8864. Min Act: 0.0000

Data Index: 1563956 (Python Code)

Max Activating Token Index: 479

Text #19

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1416604 (Python Code)

Max Activating Token Index: 742