Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1840 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1911. Min Act: -0.0002

Data Index: 228096 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1649. Min Act: -0.0002

Data Index: 446273 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1459. Min Act: -0.0002

Data Index: 268914 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1357. Min Act: -0.0002

Data Index: 732541 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1429. Min Act: -0.0002

Data Index: 1264077 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1427. Min Act: -0.0002

Data Index: 167746 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1136185 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1459. Min Act: -0.0002

Data Index: 1036508 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1298. Min Act: -0.0002

Data Index: 448705 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1413. Min Act: -0.0002

Data Index: 307907 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1389. Min Act: -0.0002

Data Index: 688006 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1254. Min Act: -0.0002

Data Index: 153992 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1388. Min Act: -0.0002

Data Index: 537478 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1175. Min Act: -0.0002

Data Index: 1280055 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1337. Min Act: -0.0002

Data Index: 65362 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1328. Min Act: -0.0002

Data Index: 860811 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1266. Min Act: -0.0002

Data Index: 916946 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1382. Min Act: -0.0002

Data Index: 810221 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1333. Min Act: -0.0002

Data Index: 1066865 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1349. Min Act: -0.0002

Data Index: 1004694 (C4 (Web Text))

Max Activating Token Index: 314