Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 736 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0004

Data Index: 672932 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0707. Min Act: -0.0003

Data Index: 363508 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0687. Min Act: -0.0003

Data Index: 98073 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0636. Min Act: -0.0004

Data Index: 849411 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0642. Min Act: -0.0003

Data Index: 898917 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0640. Min Act: -0.0003

Data Index: 1005369 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0617. Min Act: -0.0003

Data Index: 517279 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0605. Min Act: -0.0003

Data Index: 677871 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0582. Min Act: -0.0003

Data Index: 509157 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0573. Min Act: -0.0003

Data Index: 678222 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0581. Min Act: -0.0003

Data Index: 428592 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0605. Min Act: -0.0003

Data Index: 412469 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0570. Min Act: -0.0004

Data Index: 1095280 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0590. Min Act: -0.0004

Data Index: 1348168 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0557. Min Act: -0.0003

Data Index: 279304 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0553. Min Act: -0.0003

Data Index: 332 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0554. Min Act: -0.0003

Data Index: 157768 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0537. Min Act: -0.0004

Data Index: 1328828 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0545. Min Act: -0.0003

Data Index: 749534 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0548. Min Act: -0.0003

Data Index: 376596 (C4 (Web Text))

Max Activating Token Index: 615