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

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

Neuron 4206 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1647973 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1584892 (Python Code)

Max Activating Token Index: 313

Text #2

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1452242 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1518418 (Python Code)

Max Activating Token Index: 425

Text #4

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6713. Min Act: -0.0000

Data Index: 733136 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1391246 (Python Code)

Max Activating Token Index: 122

Text #6

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6027. Min Act: -0.0000

Data Index: 547986 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1442473 (Python Code)

Max Activating Token Index: 420

Text #8

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1384658 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1460508 (Python Code)

Max Activating Token Index: 1008

Text #10

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1053293 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1298557 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1186120 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5151. Min Act: -0.0000

Data Index: 60300 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5132. Min Act: -0.0000

Data Index: 140341 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1482266 (Python Code)

Max Activating Token Index: 50

Text #16

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1206093 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.4933. Min Act: -0.0000

Data Index: 21459 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1534544 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1127429 (C4 (Web Text))

Max Activating Token Index: 801