Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3396 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0379. Min Act: -0.0001

Data Index: 390141 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0314. Min Act: -0.0001

Data Index: 382516 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0298. Min Act: -0.0001

Data Index: 455820 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0346. Min Act: -0.0001

Data Index: 15762 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0335. Min Act: -0.0001

Data Index: 935154 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1148918 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0285. Min Act: -0.0001

Data Index: 79246 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0294. Min Act: -0.0001

Data Index: 447421 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0307. Min Act: -0.0001

Data Index: 519139 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0310. Min Act: -0.0001

Data Index: 804577 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1093440 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1070819 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1214512 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0243. Min Act: -0.0001

Data Index: 657002 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0269. Min Act: -0.0001

Data Index: 325361 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0244. Min Act: -0.0001

Data Index: 994386 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0274. Min Act: -0.0001

Data Index: 426516 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0228. Min Act: -0.0001

Data Index: 743527 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0262. Min Act: -0.0001

Data Index: 54217 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0262. Min Act: -0.0001

Data Index: 991784 (C4 (Web Text))

Max Activating Token Index: 84