Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 80 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0769. Min Act: -0.0001

Data Index: 568820 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0730. Min Act: -0.0001

Data Index: 779817 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0667. Min Act: -0.0001

Data Index: 741458 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0659. Min Act: -0.0001

Data Index: 730357 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0651. Min Act: -0.0001

Data Index: 141329 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1346711 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0611. Min Act: -0.0001

Data Index: 685154 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0573. Min Act: -0.0001

Data Index: 942914 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1146361 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0558. Min Act: -0.0001

Data Index: 694242 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1269354 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0553. Min Act: -0.0001

Data Index: 639888 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0542. Min Act: -0.0001

Data Index: 673411 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0564. Min Act: -0.0001

Data Index: 990357 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0520. Min Act: -0.0001

Data Index: 236174 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0542. Min Act: -0.0001

Data Index: 839667 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0529. Min Act: -0.0001

Data Index: 687559 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0514. Min Act: -0.0001

Data Index: 230351 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0521. Min Act: -0.0001

Data Index: 314727 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0507. Min Act: -0.0001

Data Index: 249098 (C4 (Web Text))

Max Activating Token Index: 798