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

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

Neuron 294 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.9019. Min Act: -0.0001

Data Index: 472395 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.9066. Min Act: -0.0001

Data Index: 738538 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.8389. Min Act: -0.0000

Data Index: 1024368 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.8929. Min Act: -0.0001

Data Index: 1295711 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.9004. Min Act: -0.0001

Data Index: 844207 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.8813. Min Act: -0.0001

Data Index: 603087 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.8051. Min Act: -0.0001

Data Index: 270480 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.3555. Min Act: -0.0000

Data Index: 1203653 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.4858. Min Act: -0.0001

Data Index: 568365 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.4287. Min Act: -0.0001

Data Index: 660977 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.4573. Min Act: -0.0000

Data Index: 229462 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.5640. Min Act: -0.0001

Data Index: 566461 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.3964. Min Act: -0.0001

Data Index: 539883 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.2134. Min Act: -0.0001

Data Index: 1065620 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.3712. Min Act: -0.0001

Data Index: 456294 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.3629. Min Act: -0.0001

Data Index: 765796 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.1131. Min Act: -0.0001

Data Index: 696804 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.2221. Min Act: -0.0001

Data Index: 942407 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.0727. Min Act: -0.0001

Data Index: 1330583 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.1656. Min Act: -0.0001

Data Index: 139388 (C4 (Web Text))

Max Activating Token Index: 810