Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4373 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1853. Min Act: -0.0002

Data Index: 1061597 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1574. Min Act: -0.0002

Data Index: 1312638 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1479. Min Act: -0.0002

Data Index: 418835 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1482. Min Act: -0.0002

Data Index: 523363 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1469. Min Act: -0.0002

Data Index: 838403 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1363. Min Act: -0.0002

Data Index: 372511 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1347. Min Act: -0.0002

Data Index: 459028 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1103784 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1503. Min Act: -0.0002

Data Index: 71616 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1368. Min Act: -0.0002

Data Index: 714248 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1364. Min Act: -0.0002

Data Index: 907864 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1321. Min Act: -0.0002

Data Index: 904713 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1345. Min Act: -0.0002

Data Index: 67218 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1390. Min Act: -0.0002

Data Index: 604226 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1234. Min Act: -0.0002

Data Index: 1022106 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1340867 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1078. Min Act: -0.0002

Data Index: 900827 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1345. Min Act: -0.0002

Data Index: 1256121 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1075. Min Act: -0.0002

Data Index: 1116371 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1125. Min Act: -0.0002

Data Index: 507450 (C4 (Web Text))

Max Activating Token Index: 185