Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3714 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0648. Min Act: -0.0001

Data Index: 789236 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0580. Min Act: -0.0001

Data Index: 119770 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0554. Min Act: -0.0001

Data Index: 134668 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0522. Min Act: -0.0001

Data Index: 709657 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0509. Min Act: -0.0001

Data Index: 179385 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0533. Min Act: -0.0001

Data Index: 872107 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0512. Min Act: -0.0001

Data Index: 355132 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0502. Min Act: -0.0001

Data Index: 416028 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0493. Min Act: -0.0001

Data Index: 699562 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1020494 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1014687 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1089134 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0455. Min Act: -0.0001

Data Index: 338410 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1343892 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0446. Min Act: -0.0001

Data Index: 201603 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0422. Min Act: -0.0001

Data Index: 615841 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0436. Min Act: -0.0001

Data Index: 372185 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0420. Min Act: -0.0001

Data Index: 8239 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0414. Min Act: -0.0001

Data Index: 181564 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0417. Min Act: -0.0001

Data Index: 269043 (C4 (Web Text))

Max Activating Token Index: 189