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

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

Neuron 2411 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: 3.4900. Min Range: -3.4900

Max Act: 3.4008. Min Act: -0.0000

Data Index: 1540930 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.4900. Min Act: -0.0000

Data Index: 1399905 (Python Code)

Max Activating Token Index: 421

Text #2

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.9756. Min Act: -0.0000

Data Index: 1601977 (Python Code)

Max Activating Token Index: 788

Text #3

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.7463. Min Act: -0.0000

Data Index: 1536078 (Python Code)

Max Activating Token Index: 815

Text #4

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.7291. Min Act: -0.0000

Data Index: 1525110 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.8068. Min Act: -0.0000

Data Index: 1596940 (Python Code)

Max Activating Token Index: 280

Text #6

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.6629. Min Act: -0.0000

Data Index: 1546988 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.4291. Min Act: -0.0000

Data Index: 1499759 (Python Code)

Max Activating Token Index: 627

Text #8

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.3359. Min Act: -0.0000

Data Index: 1456955 (Python Code)

Max Activating Token Index: 783

Text #9

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.3435. Min Act: -0.0000

Data Index: 1368447 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.2021. Min Act: -0.0000

Data Index: 1602213 (Python Code)

Max Activating Token Index: 470

Text #11

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.2498. Min Act: -0.0000

Data Index: 1458718 (Python Code)

Max Activating Token Index: 854

Text #12

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.0575. Min Act: -0.0000

Data Index: 1606186 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.1399. Min Act: -0.0000

Data Index: 1373308 (Python Code)

Max Activating Token Index: 615

Text #14

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.1999. Min Act: -0.0000

Data Index: 1557788 (Python Code)

Max Activating Token Index: 474

Text #15

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.0648. Min Act: -0.0000

Data Index: 1530644 (Python Code)

Max Activating Token Index: 901

Text #16

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.0444. Min Act: -0.0000

Data Index: 1436512 (Python Code)

Max Activating Token Index: 872

Text #17

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.1170. Min Act: -0.0000

Data Index: 1499620 (Python Code)

Max Activating Token Index: 696

Text #18

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.1749. Min Act: -0.0000

Data Index: 1557330 (Python Code)

Max Activating Token Index: 743

Text #19

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.0687. Min Act: -0.0000

Data Index: 1388093 (Python Code)

Max Activating Token Index: 828