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

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

Neuron 1536 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0755. Min Act: -0.0000

Data Index: 345660 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0759. Min Act: -0.0000

Data Index: 507997 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1002522 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1058569 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1253771 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9288. Min Act: -0.0000

Data Index: 958553 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8858. Min Act: -0.0000

Data Index: 572722 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8843. Min Act: -0.0000

Data Index: 946391 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8031. Min Act: -0.0000

Data Index: 596796 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7648. Min Act: -0.0000

Data Index: 331698 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7652. Min Act: -0.0000

Data Index: 745460 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7763. Min Act: -0.0000

Data Index: 233579 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7574. Min Act: -0.0000

Data Index: 291249 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7485. Min Act: -0.0000

Data Index: 846654 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1058201 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7136. Min Act: -0.0000

Data Index: 428312 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7485. Min Act: -0.0000

Data Index: 300048 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7259. Min Act: -0.0000

Data Index: 745386 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7201. Min Act: -0.0000

Data Index: 50899 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1347395 (C4 (Web Text))

Max Activating Token Index: 528