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

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

Neuron 1916 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.2449. Min Act: -0.0002

Data Index: 933961 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.1745. Min Act: -0.0002

Data Index: 593454 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.1856. Min Act: -0.0002

Data Index: 713513 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.1924. Min Act: -0.0001

Data Index: 311923 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8858. Min Act: -0.0002

Data Index: 674898 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8940. Min Act: -0.0002

Data Index: 605130 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8867. Min Act: -0.0001

Data Index: 735676 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8695. Min Act: -0.0001

Data Index: 471735 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8394. Min Act: -0.0002

Data Index: 495967 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8629. Min Act: -0.0002

Data Index: 634368 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8368. Min Act: -0.0002

Data Index: 247292 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8373. Min Act: -0.0001

Data Index: 325119 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8554. Min Act: -0.0002

Data Index: 1160386 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8264. Min Act: -0.0001

Data Index: 79039 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8467. Min Act: -0.0001

Data Index: 655867 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8152. Min Act: -0.0001

Data Index: 551757 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8190. Min Act: -0.0001

Data Index: 748110 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8312. Min Act: -0.0002

Data Index: 1287603 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8079. Min Act: -0.0001

Data Index: 136299 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8197. Min Act: -0.0002

Data Index: 974743 (C4 (Web Text))

Max Activating Token Index: 586