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

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

Neuron 59 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: 0.1979. Min Range: -0.1979

Max Act: 0.1979. Min Act: -0.0005

Data Index: 559310 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1733. Min Act: -0.0005

Data Index: 951463 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1860. Min Act: -0.0005

Data Index: 414177 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1581. Min Act: -0.0005

Data Index: 139508 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1734. Min Act: -0.0005

Data Index: 303008 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1536. Min Act: -0.0005

Data Index: 1329425 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1524. Min Act: -0.0005

Data Index: 408773 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1495. Min Act: -0.0005

Data Index: 851055 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1613. Min Act: -0.0005

Data Index: 693254 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1341. Min Act: -0.0005

Data Index: 801571 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1612. Min Act: -0.0005

Data Index: 501476 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1335. Min Act: -0.0005

Data Index: 801373 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1391. Min Act: -0.0005

Data Index: 1026661 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1462. Min Act: -0.0005

Data Index: 669116 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1458. Min Act: -0.0005

Data Index: 1177112 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1438. Min Act: -0.0005

Data Index: 945104 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1431. Min Act: -0.0005

Data Index: 909535 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1434. Min Act: -0.0005

Data Index: 335002 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1376. Min Act: -0.0005

Data Index: 1186313 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1232. Min Act: -0.0005

Data Index: 743786 (C4 (Web Text))

Max Activating Token Index: 309