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

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

Neuron 754 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0611. Min Act: -0.0003

Data Index: 810784 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0534. Min Act: -0.0003

Data Index: 428322 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0531. Min Act: -0.0003

Data Index: 823281 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0534. Min Act: -0.0003

Data Index: 840975 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0460. Min Act: -0.0003

Data Index: 562786 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1349711 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0532. Min Act: -0.0003

Data Index: 834974 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0479. Min Act: -0.0003

Data Index: 701573 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0494. Min Act: -0.0003

Data Index: 691946 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0514. Min Act: -0.0003

Data Index: 226781 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0510. Min Act: -0.0003

Data Index: 134582 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0492. Min Act: -0.0003

Data Index: 324651 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1334430 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0513. Min Act: -0.0003

Data Index: 449135 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0447. Min Act: -0.0003

Data Index: 782948 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0557. Min Act: -0.0003

Data Index: 465952 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1070257 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0512. Min Act: -0.0003

Data Index: 156560 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0484. Min Act: -0.0003

Data Index: 796650 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0514. Min Act: -0.0003

Data Index: 332289 (C4 (Web Text))

Max Activating Token Index: 188