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

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

Neuron 61 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6447. Min Act: 0.0000

Data Index: 1517632 (Python Code)

Max Activating Token Index: 734

Text #1

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1295288 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5773. Min Act: -0.0000

Data Index: 300809 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5602. Min Act: -0.0000

Data Index: 880874 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5455. Min Act: -0.0000

Data Index: 251052 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5863. Min Act: -0.0000

Data Index: 877806 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1082012 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1305745 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5064. Min Act: 0.0000

Data Index: 1567746 (Python Code)

Max Activating Token Index: 56

Text #9

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5149. Min Act: -0.0000

Data Index: 407670 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1550336 (Python Code)

Max Activating Token Index: 390

Text #11

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.4912. Min Act: -0.0000

Data Index: 169174 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5060. Min Act: -0.0000

Data Index: 921206 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1474999 (Python Code)

Max Activating Token Index: 382

Text #14

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.4937. Min Act: -0.0000

Data Index: 468264 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.4612. Min Act: 0.0000

Data Index: 1384439 (Python Code)

Max Activating Token Index: 905

Text #16

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1461292 (Python Code)

Max Activating Token Index: 716

Text #17

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1483936 (Python Code)

Max Activating Token Index: 666

Text #18

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.4377. Min Act: -0.0000

Data Index: 464386 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.4252. Min Act: 0.0000

Data Index: 1421204 (Python Code)

Max Activating Token Index: 523