Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 675 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2581. Min Range: -1.2581

Max Act: 1.2581. Min Act: -0.0000

Data Index: 687978 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 1.2581. Min Range: -1.2581

Max Act: 1.1609. Min Act: -0.0000

Data Index: 413313 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.2581. Min Range: -1.2581

Max Act: 1.1315. Min Act: -0.0001

Data Index: 101386 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.9946. Min Act: -0.0001

Data Index: 1073343 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.9884. Min Act: -0.0001

Data Index: 942165 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 1.2581. Min Range: -1.2581

Max Act: 1.0510. Min Act: -0.0000

Data Index: 429995 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 1.2581. Min Range: -1.2581

Max Act: 1.0273. Min Act: -0.0001

Data Index: 372817 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.2581. Min Range: -1.2581

Max Act: 1.0195. Min Act: -0.0001

Data Index: 425221 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1007071 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.9114. Min Act: -0.0000

Data Index: 56389 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.8467. Min Act: -0.0001

Data Index: 777189 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.8087. Min Act: -0.0001

Data Index: 626607 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.8546. Min Act: -0.0001

Data Index: 453483 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.8722. Min Act: -0.0000

Data Index: 328048 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.8886. Min Act: -0.0001

Data Index: 686182 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.8367. Min Act: -0.0000

Data Index: 809728 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.8305. Min Act: -0.0001

Data Index: 858300 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.7978. Min Act: -0.0001

Data Index: 1134422 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.8166. Min Act: -0.0000

Data Index: 675700 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 1.2581. Min Range: -1.2581

Max Act: 0.7511. Min Act: -0.0000

Data Index: 877509 (C4 (Web Text))

Max Activating Token Index: 848