Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1969 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0851. Min Act: -0.0001

Data Index: 627 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0619. Min Act: -0.0001

Data Index: 868464 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1150038 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1371757 (Python Code)

Max Activating Token Index: 979

Text #4

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0571. Min Act: -0.0001

Data Index: 438320 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0544. Min Act: -0.0001

Data Index: 741722 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0529. Min Act: -0.0001

Data Index: 224376 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0602. Min Act: -0.0001

Data Index: 470477 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1531793 (Python Code)

Max Activating Token Index: 654

Text #9

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0520. Min Act: -0.0001

Data Index: 570430 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1573636 (Python Code)

Max Activating Token Index: 499

Text #11

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0463. Min Act: -0.0001

Data Index: 8205 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1464420 (Python Code)

Max Activating Token Index: 902

Text #13

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1158742 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1405607 (Python Code)

Max Activating Token Index: 1014

Text #15

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0438. Min Act: -0.0001

Data Index: 296227 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0441. Min Act: -0.0001

Data Index: 170457 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0469. Min Act: -0.0001

Data Index: 287701 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1272217 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0448. Min Act: -0.0001

Data Index: 48159 (C4 (Web Text))

Max Activating Token Index: 217