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

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

Neuron 3900 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: 1.0335. Min Range: -1.0335

Max Act: 1.0335. Min Act: -0.0001

Data Index: 64554 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.8672. Min Act: -0.0001

Data Index: 674423 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.8436. Min Act: -0.0001

Data Index: 121698 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7401. Min Act: -0.0001

Data Index: 1034644 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7396. Min Act: -0.0001

Data Index: 712712 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7061. Min Act: -0.0001

Data Index: 307794 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6932. Min Act: -0.0001

Data Index: 523030 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7312. Min Act: -0.0001

Data Index: 589874 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6472. Min Act: -0.0001

Data Index: 480170 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7147. Min Act: -0.0001

Data Index: 346422 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6414. Min Act: -0.0001

Data Index: 696872 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6644. Min Act: -0.0001

Data Index: 752348 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6251. Min Act: -0.0001

Data Index: 882931 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6686. Min Act: -0.0001

Data Index: 1313327 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6400. Min Act: -0.0001

Data Index: 391631 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6162. Min Act: -0.0001

Data Index: 915844 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6184. Min Act: -0.0001

Data Index: 110224 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6626. Min Act: -0.0001

Data Index: 875918 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6001. Min Act: -0.0001

Data Index: 1110243 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.6271. Min Act: -0.0001

Data Index: 774184 (C4 (Web Text))

Max Activating Token Index: 464