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

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

Neuron 869 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4182. Min Range: -7.4182

Max Act: 7.4182. Min Act: -0.0000

Data Index: 229745 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 7.4182. Min Range: -7.4182

Max Act: 7.3490. Min Act: -0.0000

Data Index: 716096 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 7.4182. Min Range: -7.4182

Max Act: 7.3162. Min Act: -0.0000

Data Index: 278325 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.9072. Min Act: -0.0000

Data Index: 905056 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.9176. Min Act: -0.0000

Data Index: 228998 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.8891. Min Act: -0.0000

Data Index: 600287 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.4571. Min Act: -0.0000

Data Index: 10257 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.4541. Min Act: -0.0000

Data Index: 392291 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.8059. Min Act: -0.0000

Data Index: 652175 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.6219. Min Act: -0.0000

Data Index: 1231363 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.7893. Min Act: -0.0000

Data Index: 895154 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.7812. Min Act: -0.0000

Data Index: 708480 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.7370. Min Act: -0.0000

Data Index: 649503 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.4467. Min Act: -0.0000

Data Index: 271530 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.6181. Min Act: -0.0000

Data Index: 1332992 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.5918. Min Act: -0.0000

Data Index: 1187848 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.6124. Min Act: -0.0000

Data Index: 886726 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.6170. Min Act: -0.0000

Data Index: 478687 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.7825. Min Act: -0.0000

Data Index: 1260729 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 7.4182. Min Range: -7.4182

Max Act: 6.6118. Min Act: -0.0000

Data Index: 548337 (C4 (Web Text))

Max Activating Token Index: 27