Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 201 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0754. Min Act: -0.0002

Data Index: 782187 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1068368 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1009065 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0679. Min Act: -0.0002

Data Index: 806852 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0687. Min Act: -0.0001

Data Index: 360538 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0683. Min Act: -0.0002

Data Index: 668053 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0669. Min Act: -0.0002

Data Index: 477538 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1015201 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1341294 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0618. Min Act: -0.0001

Data Index: 479703 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1022334 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1047111 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0588. Min Act: -0.0002

Data Index: 90850 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0543. Min Act: -0.0001

Data Index: 693315 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0599. Min Act: -0.0001

Data Index: 25423 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0628. Min Act: -0.0002

Data Index: 879291 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0601. Min Act: -0.0002

Data Index: 721245 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1126395 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0617. Min Act: -0.0002

Data Index: 95981 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1210784 (C4 (Web Text))

Max Activating Token Index: 18