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

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

Neuron 1495 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1294048 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0612. Min Act: -0.0002

Data Index: 838130 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1244924 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0587. Min Act: -0.0002

Data Index: 903526 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0588. Min Act: -0.0002

Data Index: 528007 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0549. Min Act: -0.0002

Data Index: 687485 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0566. Min Act: -0.0002

Data Index: 430726 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0552. Min Act: -0.0002

Data Index: 36243 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0525. Min Act: -0.0002

Data Index: 365460 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0546. Min Act: -0.0002

Data Index: 506397 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0545. Min Act: -0.0001

Data Index: 569983 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1338928 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0545. Min Act: -0.0002

Data Index: 150555 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0550. Min Act: -0.0001

Data Index: 417055 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0536. Min Act: -0.0002

Data Index: 807626 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0528. Min Act: -0.0002

Data Index: 694609 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0533. Min Act: -0.0002

Data Index: 791387 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0545. Min Act: -0.0002

Data Index: 169652 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0527. Min Act: -0.0002

Data Index: 295991 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1275366 (C4 (Web Text))

Max Activating Token Index: 67