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

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

Neuron 720 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 926334 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0003

Data Index: 695623 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1212240 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1214872 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0003

Data Index: 1282472 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1421846 (Python Code)

Max Activating Token Index: 999

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0003

Data Index: 665476 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1452203 (Python Code)

Max Activating Token Index: 967

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1484497 (Python Code)

Max Activating Token Index: 1017

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0003

Data Index: 172764 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 690819 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1227073 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 445241 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1490839 (Python Code)

Max Activating Token Index: 464

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1633413 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1636377 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 588564 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1545375 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0003

Data Index: 526449 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 938767 (C4 (Web Text))

Max Activating Token Index: 974