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

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

Neuron 4548 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2014. Min Range: -6.2014

Max Act: 6.2014. Min Act: -0.0000

Data Index: 1049853 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 6.2014. Min Range: -6.2014

Max Act: 5.7553. Min Act: -0.0000

Data Index: 432525 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 6.2014. Min Range: -6.2014

Max Act: 5.6285. Min Act: -0.0000

Data Index: 1006446 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 6.2014. Min Range: -6.2014

Max Act: 5.4922. Min Act: -0.0000

Data Index: 1306748 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 6.2014. Min Range: -6.2014

Max Act: 5.2852. Min Act: -0.0000

Data Index: 389618 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 6.2014. Min Range: -6.2014

Max Act: 5.4386. Min Act: -0.0000

Data Index: 1119676 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 6.2014. Min Range: -6.2014

Max Act: 5.2454. Min Act: -0.0000

Data Index: 58559 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 6.2014. Min Range: -6.2014

Max Act: 5.2368. Min Act: -0.0000

Data Index: 62963 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 6.2014. Min Range: -6.2014

Max Act: 5.2411. Min Act: -0.0000

Data Index: 325546 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 6.2014. Min Range: -6.2014

Max Act: 5.1693. Min Act: -0.0000

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 6.2014. Min Range: -6.2014

Max Act: 5.1478. Min Act: -0.0000

Data Index: 687672 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 6.2014. Min Range: -6.2014

Max Act: 5.1124. Min Act: -0.0000

Data Index: 473521 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 6.2014. Min Range: -6.2014

Max Act: 4.8959. Min Act: -0.0000

Data Index: 926396 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 6.2014. Min Range: -6.2014

Max Act: 4.9796. Min Act: -0.0000

Data Index: 315981 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 6.2014. Min Range: -6.2014

Max Act: 4.9690. Min Act: -0.0000

Data Index: 207530 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 6.2014. Min Range: -6.2014

Max Act: 4.7487. Min Act: -0.0000

Data Index: 798457 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 6.2014. Min Range: -6.2014

Max Act: 4.9138. Min Act: -0.0000

Data Index: 91697 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 6.2014. Min Range: -6.2014

Max Act: 4.7671. Min Act: -0.0000

Data Index: 674541 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 6.2014. Min Range: -6.2014

Max Act: 4.7278. Min Act: -0.0000

Data Index: 837391 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 6.2014. Min Range: -6.2014

Max Act: 4.6826. Min Act: -0.0000

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 979