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

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

Neuron 5265 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4339. Min Range: -1.4339

Max Act: 1.4339. Min Act: -0.0000

Data Index: 331466 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 1.4339. Min Range: -1.4339

Max Act: 1.3625. Min Act: -0.0000

Data Index: 353065 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 1.4339. Min Range: -1.4339

Max Act: 1.3908. Min Act: -0.0000

Data Index: 302030 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1103298 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.9845. Min Act: -0.0000

Data Index: 375304 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.8511. Min Act: -0.0000

Data Index: 11794 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1526352 (Python Code)

Max Activating Token Index: 564

Text #7

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1612855 (Python Code)

Max Activating Token Index: 407

Text #8

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1183252 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.6485. Min Act: -0.0000

Data Index: 215622 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1562183 (Python Code)

Max Activating Token Index: 350

Text #11

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1168881 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.5951. Min Act: -0.0000

Data Index: 324131 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1091703 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1376491 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.6732. Min Act: -0.0000

Data Index: 551975 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1165197 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1502522 (Python Code)

Max Activating Token Index: 869

Text #18

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.5137. Min Act: -0.0000

Data Index: 821998 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 1.4339. Min Range: -1.4339

Max Act: 0.5330. Min Act: -0.0000

Data Index: 575862 (C4 (Web Text))

Max Activating Token Index: 77