Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 767 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0740. Min Act: -0.0002

Data Index: 838341 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0725. Min Act: -0.0002

Data Index: 761303 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0676. Min Act: -0.0002

Data Index: 3669 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0693. Min Act: -0.0002

Data Index: 36286 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0663. Min Act: -0.0002

Data Index: 517458 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0679. Min Act: -0.0002

Data Index: 361811 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0691. Min Act: -0.0002

Data Index: 383130 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1065578 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0665. Min Act: -0.0002

Data Index: 916196 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0682. Min Act: -0.0002

Data Index: 492758 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0677. Min Act: -0.0002

Data Index: 195524 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0657. Min Act: -0.0002

Data Index: 155195 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0659. Min Act: -0.0002

Data Index: 804775 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0653. Min Act: -0.0002

Data Index: 755775 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1159348 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0623. Min Act: -0.0002

Data Index: 478075 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0637. Min Act: -0.0002

Data Index: 809542 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0645. Min Act: -0.0002

Data Index: 282090 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0627. Min Act: -0.0002

Data Index: 475483 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0615. Min Act: -0.0002

Data Index: 86300 (C4 (Web Text))

Max Activating Token Index: 885