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

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

Neuron 4868 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1528118 (Python Code)

Max Activating Token Index: 977

Text #1

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0685. Min Act: -0.0001

Data Index: 997897 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1091456 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1341003 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0655. Min Act: -0.0001

Data Index: 744768 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1523484 (Python Code)

Max Activating Token Index: 630

Text #6

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1618831 (Python Code)

Max Activating Token Index: 298

Text #7

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1232202 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1452042 (Python Code)

Max Activating Token Index: 950

Text #9

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1067436 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0555. Min Act: -0.0001

Data Index: 962004 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0557. Min Act: -0.0001

Data Index: 353308 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1299194 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0504. Min Act: -0.0001

Data Index: 868224 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0497. Min Act: -0.0001

Data Index: 379745 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0534. Min Act: -0.0001

Data Index: 328106 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0555. Min Act: -0.0001

Data Index: 148039 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1022061 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0488. Min Act: -0.0001

Data Index: 380929 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1228596 (C4 (Web Text))

Max Activating Token Index: 188