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

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

Neuron 1038 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1000030 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.8117. Min Act: 0.0000

Data Index: 808468 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.8106. Min Act: -0.0000

Data Index: 862896 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7744. Min Act: 0.0001

Data Index: 900049 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7442. Min Act: -0.0000

Data Index: 403523 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7316. Min Act: -0.0000

Data Index: 97726 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7981. Min Act: -0.0000

Data Index: 383474 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7039. Min Act: -0.0000

Data Index: 310889 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1356839 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6469. Min Act: 0.0001

Data Index: 668056 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6625. Min Act: -0.0000

Data Index: 160236 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6541. Min Act: -0.0000

Data Index: 270536 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6598. Min Act: 0.0000

Data Index: 269147 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6154. Min Act: -0.0000

Data Index: 164310 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1164689 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1211340 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6261. Min Act: -0.0000

Data Index: 180904 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.5859. Min Act: -0.0001

Data Index: 679376 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6112. Min Act: -0.0000

Data Index: 293737 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1116344 (C4 (Web Text))

Max Activating Token Index: 421