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

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

Neuron 2362 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1543. Min Range: -6.1543

Max Act: 6.0899. Min Act: -0.0000

Data Index: 55648 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 6.1543. Min Range: -6.1543

Max Act: 6.1543. Min Act: -0.0000

Data Index: 87382 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 6.1543. Min Range: -6.1543

Max Act: 5.3623. Min Act: -0.0000

Data Index: 619044 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 6.1543. Min Range: -6.1543

Max Act: 5.1132. Min Act: -0.0000

Data Index: 235882 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.8094. Min Act: -0.0000

Data Index: 905884 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.8864. Min Act: -0.0000

Data Index: 559029 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.4640. Min Act: -0.0000

Data Index: 715860 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.6430. Min Act: -0.0000

Data Index: 454610 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.4482. Min Act: 0.0000

Data Index: 991445 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.9983. Min Act: -0.0000

Data Index: 726402 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 6.1543. Min Range: -6.1543

Max Act: 3.8652. Min Act: -0.0000

Data Index: 190250 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.7531. Min Act: -0.0000

Data Index: 157462 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.5119. Min Act: -0.0000

Data Index: 351415 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.2967. Min Act: -0.0000

Data Index: 804254 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.3038. Min Act: -0.0000

Data Index: 616961 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.6553. Min Act: -0.0000

Data Index: 475232 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.2225. Min Act: -0.0000

Data Index: 1171027 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.1589. Min Act: -0.0000

Data Index: 992509 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.5193. Min Act: -0.0000

Data Index: 32757 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 6.1543. Min Range: -6.1543

Max Act: 4.2665. Min Act: -0.0000

Data Index: 134600 (C4 (Web Text))

Max Activating Token Index: 493