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

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

Neuron 4848 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1627897 (Python Code)

Max Activating Token Index: 946

Text #1

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4802. Min Act: -0.0000

Data Index: 618911 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.3800. Min Act: -0.0001

Data Index: 1590369 (Python Code)

Max Activating Token Index: 270

Text #3

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4007. Min Act: -0.0001

Data Index: 1444893 (Python Code)

Max Activating Token Index: 347

Text #4

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4071. Min Act: -0.0001

Data Index: 1531448 (Python Code)

Max Activating Token Index: 305

Text #5

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1545377 (Python Code)

Max Activating Token Index: 681

Text #6

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1387702 (Python Code)

Max Activating Token Index: 577

Text #7

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1500225 (Python Code)

Max Activating Token Index: 914

Text #8

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1456880 (Python Code)

Max Activating Token Index: 853

Text #9

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.3433. Min Act: -0.0001

Data Index: 1639003 (Python Code)

Max Activating Token Index: 358

Text #10

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1499482 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.2566. Min Act: -0.0001

Data Index: 1422816 (Python Code)

Max Activating Token Index: 100

Text #12

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.2231. Min Act: -0.0000

Data Index: 704955 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1501115 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1017712 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.2064. Min Act: -0.0000

Data Index: 739327 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.2043. Min Act: -0.0000

Data Index: 718555 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.2078. Min Act: -0.0000

Data Index: 730143 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.2021. Min Act: -0.0000

Data Index: 967773 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1198195 (C4 (Web Text))

Max Activating Token Index: 631