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

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

Neuron 1103 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1081331 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1086832 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0967. Min Act: -0.0001

Data Index: 887669 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0817. Min Act: -0.0001

Data Index: 603618 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0910. Min Act: -0.0001

Data Index: 22975 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1490684 (Python Code)

Max Activating Token Index: 396

Text #6

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1382967 (Python Code)

Max Activating Token Index: 791

Text #7

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0885. Min Act: -0.0001

Data Index: 146783 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1118766 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0667. Min Act: -0.0001

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1024601 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0861. Min Act: -0.0001

Data Index: 522905 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0737. Min Act: -0.0001

Data Index: 459235 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0785. Min Act: -0.0000

Data Index: 860497 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0779. Min Act: -0.0001

Data Index: 1616037 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1575730 (Python Code)

Max Activating Token Index: 700

Text #16

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0725. Min Act: -0.0001

Data Index: 490973 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0747. Min Act: -0.0001

Data Index: 248739 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0733. Min Act: -0.0000

Data Index: 831507 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0958. Min Act: -0.0001

Data Index: 921999 (C4 (Web Text))

Max Activating Token Index: 819