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

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

Neuron 4638 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.4485. Min Act: -0.0000

Data Index: 1117949 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.0213. Min Act: -0.0000

Data Index: 200703 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.1203. Min Act: -0.0000

Data Index: 50711 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9420. Min Act: -0.0000

Data Index: 556631 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9769. Min Act: -0.0000

Data Index: 689837 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1086459 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8570. Min Act: -0.0000

Data Index: 739909 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9104. Min Act: -0.0000

Data Index: 130470 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9610. Min Act: -0.0000

Data Index: 283561 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1324337 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8494. Min Act: -0.0000

Data Index: 324517 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8916. Min Act: -0.0000

Data Index: 607696 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8256. Min Act: -0.0000

Data Index: 236356 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1035019 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9417. Min Act: -0.0000

Data Index: 641004 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9268. Min Act: -0.0000

Data Index: 385887 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9305. Min Act: -0.0000

Data Index: 128174 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8282. Min Act: -0.0000

Data Index: 354356 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8613. Min Act: -0.0000

Data Index: 399229 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1293415 (C4 (Web Text))

Max Activating Token Index: 561