Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4415 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1451. Min Range: -2.1451

Max Act: 2.1387. Min Act: -0.0000

Data Index: 248414 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 2.1451. Min Range: -2.1451

Max Act: 2.1451. Min Act: -0.0001

Data Index: 953909 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.7673. Min Act: -0.0000

Data Index: 1121161 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.5510. Min Act: -0.0000

Data Index: 994620 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.3668. Min Act: -0.0000

Data Index: 822528 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.7376. Min Act: -0.0000

Data Index: 1156596 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.5362. Min Act: -0.0000

Data Index: 365671 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.5516. Min Act: -0.0000

Data Index: 1262376 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.6671. Min Act: -0.0000

Data Index: 225924 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.4160. Min Act: -0.0000

Data Index: 20065 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.6460. Min Act: -0.0000

Data Index: 581501 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.5478. Min Act: -0.0001

Data Index: 1044996 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.6233. Min Act: -0.0000

Data Index: 325686 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.6234. Min Act: -0.0000

Data Index: 1059276 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.6684. Min Act: -0.0000

Data Index: 209575 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1066764 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.4857. Min Act: -0.0001

Data Index: 612647 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.4890. Min Act: -0.0000

Data Index: 51156 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.6883. Min Act: -0.0000

Data Index: 1032418 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 2.1451. Min Range: -2.1451

Max Act: 1.5786. Min Act: -0.0001

Data Index: 1315136 (C4 (Web Text))

Max Activating Token Index: 635