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

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

Neuron 263 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0591. Min Act: -0.0005

Data Index: 448019 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0619. Min Act: -0.0004

Data Index: 179008 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0571. Min Act: -0.0004

Data Index: 1154617 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0601. Min Act: -0.0004

Data Index: 1205776 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0588. Min Act: -0.0005

Data Index: 875650 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0553. Min Act: -0.0004

Data Index: 947107 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0564. Min Act: -0.0005

Data Index: 16479 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0538. Min Act: -0.0005

Data Index: 444676 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0521. Min Act: -0.0005

Data Index: 30994 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0512. Min Act: -0.0004

Data Index: 344871 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0516. Min Act: -0.0005

Data Index: 936126 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0474. Min Act: -0.0005

Data Index: 964781 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0484. Min Act: -0.0005

Data Index: 679960 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0510. Min Act: -0.0005

Data Index: 909420 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0505. Min Act: -0.0004

Data Index: 252230 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0497. Min Act: -0.0004

Data Index: 1259665 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0489. Min Act: -0.0005

Data Index: 977267 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0465. Min Act: -0.0005

Data Index: 901970 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0491. Min Act: -0.0005

Data Index: 787592 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0482. Min Act: -0.0005

Data Index: 706322 (C4 (Web Text))

Max Activating Token Index: 292