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

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

Neuron 4050 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.2547. Min Act: -0.0001

Data Index: 60494 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.2603. Min Act: -0.0001

Data Index: 361940 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.2249. Min Act: -0.0001

Data Index: 1565511 (Python Code)

Max Activating Token Index: 294

Text #3

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.1359. Min Act: -0.0001

Data Index: 1446597 (Python Code)

Max Activating Token Index: 825

Text #4

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.1323. Min Act: -0.0001

Data Index: 471137 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.1086. Min Act: -0.0001

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.1826. Min Act: -0.0001

Data Index: 1454274 (Python Code)

Max Activating Token Index: 274

Text #7

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.1134. Min Act: -0.0001

Data Index: 439284 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.1187. Min Act: -0.0001

Data Index: 793720 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.1133. Min Act: -0.0001

Data Index: 1462797 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.1219. Min Act: -0.0001

Data Index: 450480 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.1413. Min Act: -0.0001

Data Index: 634433 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.0929. Min Act: -0.0001

Data Index: 1554829 (Python Code)

Max Activating Token Index: 376

Text #13

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.0732. Min Act: -0.0001

Data Index: 266841 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.0637. Min Act: -0.0001

Data Index: 378072 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.0651. Min Act: -0.0001

Data Index: 1420826 (Python Code)

Max Activating Token Index: 1016

Text #16

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.0209. Min Act: -0.0001

Data Index: 79109 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.9860. Min Act: -0.0001

Data Index: 1464469 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.9745. Min Act: -0.0001

Data Index: 1455531 (Python Code)

Max Activating Token Index: 124

Text #19

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.0331. Min Act: -0.0001

Data Index: 1619746 (Python Code)

Max Activating Token Index: 672