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

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

Neuron 4254 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: 2.6973. Min Range: -2.6973

Max Act: 2.6973. Min Act: -0.0000

Data Index: 1372075 (Python Code)

Max Activating Token Index: 555

Text #1

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.6856. Min Act: -0.0000

Data Index: 1531177 (Python Code)

Max Activating Token Index: 381

Text #2

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.2776. Min Act: -0.0000

Data Index: 1413643 (Python Code)

Max Activating Token Index: 315

Text #3

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.4862. Min Act: -0.0000

Data Index: 1269149 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.3043. Min Act: -0.0000

Data Index: 1442334 (Python Code)

Max Activating Token Index: 666

Text #5

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.3919. Min Act: -0.0000

Data Index: 1482618 (Python Code)

Max Activating Token Index: 907

Text #6

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.0917. Min Act: -0.0000

Data Index: 1468570 (Python Code)

Max Activating Token Index: 886

Text #7

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.1356. Min Act: -0.0000

Data Index: 1625243 (Python Code)

Max Activating Token Index: 487

Text #8

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.1910. Min Act: -0.0000

Data Index: 1560965 (Python Code)

Max Activating Token Index: 511

Text #9

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.1574. Min Act: -0.0000

Data Index: 1128531 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.1317. Min Act: -0.0000

Data Index: 1508565 (Python Code)

Max Activating Token Index: 983

Text #11

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.0402. Min Act: -0.0000

Data Index: 1481478 (Python Code)

Max Activating Token Index: 444

Text #12

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.1468. Min Act: -0.0000

Data Index: 1455937 (Python Code)

Max Activating Token Index: 268

Text #13

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.0785. Min Act: -0.0000

Data Index: 1549150 (Python Code)

Max Activating Token Index: 997

Text #14

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.1264. Min Act: -0.0000

Data Index: 1438580 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.1080. Min Act: -0.0000

Data Index: 1527760 (Python Code)

Max Activating Token Index: 950

Text #16

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.0452. Min Act: -0.0000

Data Index: 1399711 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.0605. Min Act: -0.0000

Data Index: 374986 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.0902. Min Act: -0.0000

Data Index: 1597803 (Python Code)

Max Activating Token Index: 978

Text #19

Max Range: 2.6973. Min Range: -2.6973

Max Act: 2.0639. Min Act: -0.0000

Data Index: 1405860 (Python Code)

Max Activating Token Index: 749