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

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

Neuron 1595 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: 2.0733. Min Range: -2.0733

Max Act: 2.0733. Min Act: -0.0001

Data Index: 315171 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.8472. Min Act: -0.0000

Data Index: 947408 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.6353. Min Act: -0.0001

Data Index: 1106152 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.3495. Min Act: -0.0000

Data Index: 1174008 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.5178. Min Act: -0.0000

Data Index: 704384 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.4959. Min Act: -0.0000

Data Index: 1113043 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.5445. Min Act: -0.0000

Data Index: 881652 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.5300. Min Act: -0.0001

Data Index: 319331 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.6073. Min Act: -0.0000

Data Index: 1252673 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.5097. Min Act: -0.0000

Data Index: 1245056 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.5034. Min Act: -0.0000

Data Index: 106257 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.5642. Min Act: -0.0000

Data Index: 415685 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.5658. Min Act: -0.0000

Data Index: 658478 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.3796. Min Act: -0.0000

Data Index: 1092214 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.3484. Min Act: -0.0000

Data Index: 1116663 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.5132. Min Act: -0.0000

Data Index: 787546 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.3904. Min Act: -0.0000

Data Index: 363903 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.4388. Min Act: -0.0000

Data Index: 360562 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.3632. Min Act: -0.0000

Data Index: 603964 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 2.0733. Min Range: -2.0733

Max Act: 1.3488. Min Act: -0.0000

Data Index: 206286 (C4 (Web Text))

Max Activating Token Index: 1023