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

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

Neuron 4984 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0773. Min Act: -0.0003

Data Index: 408595 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0770. Min Act: -0.0003

Data Index: 687347 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0719. Min Act: -0.0003

Data Index: 526532 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0720. Min Act: -0.0003

Data Index: 342473 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0708. Min Act: -0.0003

Data Index: 419741 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1106054 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0679. Min Act: -0.0003

Data Index: 675197 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0693. Min Act: -0.0003

Data Index: 472713 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0689. Min Act: -0.0003

Data Index: 843385 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0671. Min Act: -0.0003

Data Index: 568210 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0665. Min Act: -0.0002

Data Index: 939559 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0654. Min Act: -0.0003

Data Index: 724249 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0662. Min Act: -0.0003

Data Index: 518574 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0669. Min Act: -0.0003

Data Index: 1037966 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0643. Min Act: -0.0003

Data Index: 570869 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1144477 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1008634 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0640. Min Act: -0.0003

Data Index: 696028 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0663. Min Act: -0.0003

Data Index: 866387 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0653. Min Act: -0.0003

Data Index: 71514 (C4 (Web Text))

Max Activating Token Index: 423