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

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

Neuron 2593 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 6.8701. Min Range: -6.8701

Max Act: 6.8701. Min Act: -0.0001

Data Index: 1137517 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 6.8701. Min Range: -6.8701

Max Act: 5.8118. Min Act: -0.0000

Data Index: 848617 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 6.8701. Min Range: -6.8701

Max Act: 5.1742. Min Act: -0.0001

Data Index: 662853 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 6.8701. Min Range: -6.8701

Max Act: 5.5214. Min Act: 0.0001

Data Index: 474858 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 6.8701. Min Range: -6.8701

Max Act: 5.3328. Min Act: 0.0001

Data Index: 1301435 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 6.8701. Min Range: -6.8701

Max Act: 5.1423. Min Act: -0.0001

Data Index: 456158 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 6.8701. Min Range: -6.8701

Max Act: 5.3011. Min Act: -0.0000

Data Index: 815580 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 6.8701. Min Range: -6.8701

Max Act: 5.0927. Min Act: -0.0000

Data Index: 1298786 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 6.8701. Min Range: -6.8701

Max Act: 5.3833. Min Act: -0.0000

Data Index: 1283499 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 6.8701. Min Range: -6.8701

Max Act: 5.0466. Min Act: -0.0001

Data Index: 497849 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 6.8701. Min Range: -6.8701

Max Act: 5.0512. Min Act: -0.0000

Data Index: 72418 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 6.8701. Min Range: -6.8701

Max Act: 4.8434. Min Act: 0.0001

Data Index: 867702 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 6.8701. Min Range: -6.8701

Max Act: 5.3369. Min Act: -0.0000

Data Index: 1078057 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 6.8701. Min Range: -6.8701

Max Act: 4.8118. Min Act: -0.0000

Data Index: 55351 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 6.8701. Min Range: -6.8701

Max Act: 4.8627. Min Act: -0.0001

Data Index: 708114 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 6.8701. Min Range: -6.8701

Max Act: 4.8420. Min Act: -0.0000

Data Index: 1057916 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 6.8701. Min Range: -6.8701

Max Act: 4.6386. Min Act: -0.0001

Data Index: 437379 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 6.8701. Min Range: -6.8701

Max Act: 4.6519. Min Act: -0.0000

Data Index: 395264 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 6.8701. Min Range: -6.8701

Max Act: 4.8027. Min Act: -0.0000

Data Index: 1222123 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 6.8701. Min Range: -6.8701

Max Act: 4.7245. Min Act: -0.0000

Data Index: 764484 (C4 (Web Text))

Max Activating Token Index: 152