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

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

Neuron 602 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: 1.1000. Min Range: -1.1000

Max Act: 1.1000. Min Act: -0.0002

Data Index: 75557 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 1.1000. Min Range: -1.1000

Max Act: 1.0973. Min Act: -0.0002

Data Index: 994655 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 1.1000. Min Range: -1.1000

Max Act: 1.0195. Min Act: -0.0002

Data Index: 862049 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 1.1000. Min Range: -1.1000

Max Act: 1.0116. Min Act: -0.0002

Data Index: 752194 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.1000. Min Range: -1.1000

Max Act: 1.0247. Min Act: -0.0001

Data Index: 423454 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.9705. Min Act: -0.0001

Data Index: 1075990 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.8945. Min Act: -0.0002

Data Index: 713685 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.9198. Min Act: -0.0002

Data Index: 810000 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.9280. Min Act: -0.0002

Data Index: 208754 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.7956. Min Act: -0.0002

Data Index: 186548 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.7779. Min Act: -0.0002

Data Index: 664204 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.8139. Min Act: -0.0001

Data Index: 392180 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.8212. Min Act: -0.0002

Data Index: 1351789 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.8231. Min Act: -0.0002

Data Index: 245067 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.8076. Min Act: -0.0002

Data Index: 1270739 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.7619. Min Act: -0.0002

Data Index: 190313 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.7924. Min Act: -0.0002

Data Index: 852415 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.7927. Min Act: -0.0001

Data Index: 174405 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.7833. Min Act: -0.0002

Data Index: 345391 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 1.1000. Min Range: -1.1000

Max Act: 0.7555. Min Act: -0.0001

Data Index: 402203 (C4 (Web Text))

Max Activating Token Index: 72