Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5385 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0632. Min Act: -0.0002

Data Index: 386272 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0644. Min Act: -0.0002

Data Index: 55154 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0636. Min Act: -0.0002

Data Index: 678240 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0633. Min Act: -0.0002

Data Index: 342894 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1297712 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0584. Min Act: -0.0002

Data Index: 79568 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0567. Min Act: -0.0002

Data Index: 557886 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0577. Min Act: -0.0002

Data Index: 598138 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0578. Min Act: -0.0002

Data Index: 509878 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1055772 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0586. Min Act: -0.0002

Data Index: 748697 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1281638 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0555. Min Act: -0.0002

Data Index: 4761 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0529. Min Act: -0.0002

Data Index: 609519 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0541. Min Act: -0.0002

Data Index: 690603 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0541. Min Act: -0.0002

Data Index: 441170 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0535. Min Act: -0.0002

Data Index: 409424 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0509. Min Act: -0.0002

Data Index: 181331 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1215399 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1333583 (C4 (Web Text))

Max Activating Token Index: 134