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

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

Neuron 1430 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.8328. Min Act: -0.0000

Data Index: 310734 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.7318. Min Act: -0.0000

Data Index: 1231792 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.4694. Min Act: -0.0000

Data Index: 1387101 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.3557. Min Act: -0.0000

Data Index: 823666 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.3120. Min Act: -0.0000

Data Index: 306097 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.2753. Min Act: -0.0000

Data Index: 1486392 (Python Code)

Max Activating Token Index: 476

Text #6

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1420401 (Python Code)

Max Activating Token Index: 378

Text #7

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.2971. Min Act: -0.0000

Data Index: 1527672 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.1966. Min Act: -0.0000

Data Index: 51110 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.2192. Min Act: -0.0000

Data Index: 426986 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.1908. Min Act: -0.0000

Data Index: 1249989 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.1298. Min Act: -0.0000

Data Index: 483757 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1102378 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.1474. Min Act: -0.0000

Data Index: 1409063 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1509517 (Python Code)

Max Activating Token Index: 835

Text #15

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.1069. Min Act: -0.0000

Data Index: 1570734 (Python Code)

Max Activating Token Index: 648

Text #16

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.0902. Min Act: -0.0000

Data Index: 255475 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.1466. Min Act: -0.0000

Data Index: 1491334 (Python Code)

Max Activating Token Index: 780

Text #18

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.1053. Min Act: -0.0000

Data Index: 1651976 (Python Code)

Max Activating Token Index: 386

Text #19

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1419682 (Python Code)

Max Activating Token Index: 426