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

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

Neuron 639 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: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0005

Data Index: 958530 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0623. Min Act: -0.0004

Data Index: 1170032 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0642. Min Act: -0.0003

Data Index: 1270520 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0628. Min Act: -0.0003

Data Index: 1352548 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0615. Min Act: -0.0004

Data Index: 1165236 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0612. Min Act: -0.0003

Data Index: 453726 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0588. Min Act: -0.0004

Data Index: 199006 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0582. Min Act: -0.0004

Data Index: 633785 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0580. Min Act: -0.0004

Data Index: 722316 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0541. Min Act: -0.0004

Data Index: 755830 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0543. Min Act: -0.0004

Data Index: 1198248 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0571. Min Act: -0.0004

Data Index: 322992 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1306940 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0556. Min Act: -0.0003

Data Index: 269743 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0527. Min Act: -0.0003

Data Index: 379728 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0527. Min Act: -0.0003

Data Index: 233189 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0517. Min Act: -0.0004

Data Index: 730457 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0520. Min Act: -0.0004

Data Index: 1284648 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1032254 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0520. Min Act: -0.0003

Data Index: 552395 (C4 (Web Text))

Max Activating Token Index: 84