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

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

Neuron 1628 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0003. Min Range: -1.0003

Max Act: 1.0003. Min Act: -0.0001

Data Index: 679126 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8701. Min Act: -0.0001

Data Index: 477185 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8563. Min Act: -0.0001

Data Index: 183512 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8448. Min Act: -0.0001

Data Index: 196895 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7924. Min Act: -0.0001

Data Index: 213256 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7705. Min Act: -0.0001

Data Index: 233971 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7705. Min Act: -0.0001

Data Index: 1073407 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7426. Min Act: -0.0001

Data Index: 1230049 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6761. Min Act: -0.0001

Data Index: 1043078 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6618. Min Act: -0.0001

Data Index: 1205371 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7093. Min Act: -0.0001

Data Index: 449792 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6876. Min Act: -0.0001

Data Index: 1035258 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6829. Min Act: -0.0001

Data Index: 128123 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.5845. Min Act: -0.0001

Data Index: 18587 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7248. Min Act: -0.0001

Data Index: 558950 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1275545 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7627. Min Act: -0.0001

Data Index: 970037 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6022. Min Act: -0.0001

Data Index: 1238667 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6335. Min Act: -0.0001

Data Index: 463404 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6295. Min Act: -0.0001

Data Index: 1325579 (C4 (Web Text))

Max Activating Token Index: 385