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

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

Neuron 5727 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6631. Min Range: -4.6631

Max Act: 4.6432. Min Act: -0.0000

Data Index: 678300 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 4.6631. Min Range: -4.6631

Max Act: 4.6631. Min Act: -0.0000

Data Index: 57256 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.8000. Min Act: -0.0000

Data Index: 540598 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.8398. Min Act: -0.0000

Data Index: 540126 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.7938. Min Act: -0.0000

Data Index: 1088168 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.7161. Min Act: -0.0000

Data Index: 877468 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.8699. Min Act: -0.0000

Data Index: 355986 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.6585. Min Act: -0.0000

Data Index: 974728 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.6229. Min Act: -0.0000

Data Index: 324256 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.7194. Min Act: -0.0000

Data Index: 647306 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.5231. Min Act: -0.0000

Data Index: 184971 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.5167. Min Act: -0.0000

Data Index: 156858 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.1818. Min Act: -0.0000

Data Index: 1265946 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.3188. Min Act: 0.0000

Data Index: 257297 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.3090. Min Act: -0.0000

Data Index: 267959 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.3006. Min Act: -0.0000

Data Index: 345206 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.1028. Min Act: -0.0000

Data Index: 603007 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.0973. Min Act: -0.0000

Data Index: 1271435 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.2323. Min Act: -0.0000

Data Index: 839953 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 4.6631. Min Range: -4.6631

Max Act: 3.0552. Min Act: -0.0000

Data Index: 943936 (C4 (Web Text))

Max Activating Token Index: 935