Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4302 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0744. Min Act: -0.0002

Data Index: 963046 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0684. Min Act: -0.0002

Data Index: 571506 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0588. Min Act: -0.0002

Data Index: 887207 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0565. Min Act: -0.0002

Data Index: 48693 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0559. Min Act: -0.0002

Data Index: 315521 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0541. Min Act: -0.0002

Data Index: 396137 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1051047 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1064230 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1152200 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0531. Min Act: -0.0002

Data Index: 226299 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0472. Min Act: -0.0002

Data Index: 841006 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0456. Min Act: -0.0002

Data Index: 60494 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0431. Min Act: -0.0002

Data Index: 465300 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0452. Min Act: -0.0002

Data Index: 537561 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0455. Min Act: -0.0002

Data Index: 915942 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0445. Min Act: -0.0002

Data Index: 967222 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1294630 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1301191 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1050986 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0434. Min Act: -0.0002

Data Index: 258717 (C4 (Web Text))

Max Activating Token Index: 494