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

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

Neuron 3271 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2243. Min Range: -1.2243

Max Act: 1.2243. Min Act: -0.0001

Data Index: 1321786 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 1.2243. Min Range: -1.2243

Max Act: 1.1256. Min Act: -0.0001

Data Index: 220316 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 1.2243. Min Range: -1.2243

Max Act: 1.0505. Min Act: -0.0001

Data Index: 691443 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9228. Min Act: -0.0001

Data Index: 279060 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9175. Min Act: -0.0001

Data Index: 439365 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9341. Min Act: -0.0001

Data Index: 774610 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9516. Min Act: -0.0001

Data Index: 1246977 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9091. Min Act: -0.0001

Data Index: 315549 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9149. Min Act: -0.0001

Data Index: 1194501 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8733. Min Act: -0.0001

Data Index: 1011418 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8602. Min Act: -0.0001

Data Index: 654129 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8551. Min Act: -0.0001

Data Index: 730670 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8535. Min Act: -0.0001

Data Index: 561323 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8266. Min Act: -0.0001

Data Index: 34970 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9072. Min Act: -0.0001

Data Index: 1347304 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8506. Min Act: -0.0001

Data Index: 21804 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8344. Min Act: -0.0001

Data Index: 1302855 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8096. Min Act: -0.0001

Data Index: 1082457 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8115. Min Act: -0.0001

Data Index: 391730 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8696. Min Act: -0.0001

Data Index: 1066624 (C4 (Web Text))

Max Activating Token Index: 84