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

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

Neuron 632 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2283. Min Range: -2.2283

Max Act: 2.2283. Min Act: -0.0000

Data Index: 15276 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 2.2283. Min Range: -2.2283

Max Act: 2.1386. Min Act: -0.0000

Data Index: 808532 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 2.2283. Min Range: -2.2283

Max Act: 2.0116. Min Act: -0.0000

Data Index: 345622 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.7702. Min Act: -0.0000

Data Index: 1555350 (Python Code)

Max Activating Token Index: 923

Text #4

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.7436. Min Act: -0.0000

Data Index: 916541 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.7337. Min Act: -0.0000

Data Index: 329555 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.5504. Min Act: -0.0000

Data Index: 759331 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.5836. Min Act: -0.0000

Data Index: 287885 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.4875. Min Act: -0.0000

Data Index: 1567498 (Python Code)

Max Activating Token Index: 348

Text #9

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.5527. Min Act: -0.0000

Data Index: 132858 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.5259. Min Act: -0.0000

Data Index: 682813 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.6144. Min Act: -0.0000

Data Index: 1126651 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.5103. Min Act: -0.0000

Data Index: 308744 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.5114. Min Act: -0.0000

Data Index: 251637 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.4838. Min Act: -0.0000

Data Index: 993883 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.4740. Min Act: -0.0001

Data Index: 459962 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.4773. Min Act: -0.0000

Data Index: 775183 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.4417. Min Act: -0.0000

Data Index: 1443231 (Python Code)

Max Activating Token Index: 779

Text #18

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.5628. Min Act: -0.0000

Data Index: 1339981 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 2.2283. Min Range: -2.2283

Max Act: 1.3889. Min Act: -0.0000

Data Index: 349288 (C4 (Web Text))

Max Activating Token Index: 799