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

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

Neuron 3424 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: 0.2358. Min Range: -0.2358

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1012844 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2324. Min Act: -0.0000

Data Index: 986438 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2251. Min Act: -0.0000

Data Index: 182452 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2205. Min Act: -0.0000

Data Index: 336241 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2184. Min Act: -0.0001

Data Index: 777949 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1349150 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2115. Min Act: -0.0001

Data Index: 1268704 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1981. Min Act: -0.0000

Data Index: 602546 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1952. Min Act: -0.0000

Data Index: 931299 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1873. Min Act: -0.0000

Data Index: 109642 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1012629 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1882. Min Act: -0.0000

Data Index: 293037 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1786. Min Act: -0.0000

Data Index: 430250 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1727. Min Act: -0.0000

Data Index: 594956 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1691. Min Act: -0.0000

Data Index: 77498 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1148987 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1743. Min Act: -0.0001

Data Index: 833175 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1861. Min Act: -0.0000

Data Index: 758446 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1728. Min Act: -0.0000

Data Index: 90786 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1658. Min Act: -0.0000

Data Index: 608219 (C4 (Web Text))

Max Activating Token Index: 578