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

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

Neuron 1118 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: 0.0833. Min Range: -0.0833

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1343947 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0744. Min Act: -0.0001

Data Index: 106753 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1081792 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0708. Min Act: -0.0001

Data Index: 674740 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0662. Min Act: -0.0001

Data Index: 961720 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0644. Min Act: -0.0001

Data Index: 721634 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0638. Min Act: -0.0001

Data Index: 508794 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0620. Min Act: -0.0001

Data Index: 191436 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0606. Min Act: -0.0001

Data Index: 846133 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0600. Min Act: -0.0001

Data Index: 30947 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0623. Min Act: -0.0001

Data Index: 263464 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0584. Min Act: -0.0000

Data Index: 526856 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0613. Min Act: -0.0001

Data Index: 78844 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0568. Min Act: -0.0001

Data Index: 466989 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0482. Min Act: -0.0001

Data Index: 261866 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0536. Min Act: -0.0001

Data Index: 683059 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0562. Min Act: -0.0001

Data Index: 251143 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1172510 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1095040 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1151619 (C4 (Web Text))

Max Activating Token Index: 315