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

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

Neuron 152 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: 0.2450. Min Range: -0.2450

Max Act: 0.2450. Min Act: -0.0001

Data Index: 474880 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2224. Min Act: -0.0001

Data Index: 341867 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2207. Min Act: -0.0001

Data Index: 723936 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2080. Min Act: -0.0001

Data Index: 558824 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2001. Min Act: -0.0001

Data Index: 457976 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2123. Min Act: -0.0001

Data Index: 345328 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1824. Min Act: -0.0001

Data Index: 945912 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1880. Min Act: -0.0001

Data Index: 621279 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2041. Min Act: -0.0001

Data Index: 270570 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1809. Min Act: -0.0001

Data Index: 1231612 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2130. Min Act: -0.0001

Data Index: 130206 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1870. Min Act: -0.0001

Data Index: 513569 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1864. Min Act: -0.0001

Data Index: 957992 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1899. Min Act: -0.0001

Data Index: 306419 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1903. Min Act: -0.0001

Data Index: 657091 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1793. Min Act: -0.0001

Data Index: 901877 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1627. Min Act: -0.0001

Data Index: 557008 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1799. Min Act: -0.0001

Data Index: 770965 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1742. Min Act: -0.0001

Data Index: 166838 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1708. Min Act: -0.0001

Data Index: 755090 (C4 (Web Text))

Max Activating Token Index: 166