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

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

Neuron 5764 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0001

Data Index: 861538 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0489. Min Act: -0.0001

Data Index: 330996 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0501. Min Act: -0.0001

Data Index: 699453 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0427. Min Act: -0.0001

Data Index: 415230 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0364. Min Act: -0.0001

Data Index: 886506 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1216590 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0302. Min Act: -0.0001

Data Index: 722364 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0332. Min Act: -0.0001

Data Index: 791196 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0346. Min Act: -0.0001

Data Index: 953089 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0293. Min Act: -0.0001

Data Index: 404861 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0304. Min Act: -0.0001

Data Index: 353529 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0279. Min Act: -0.0001

Data Index: 68199 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0304. Min Act: -0.0001

Data Index: 936388 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0315. Min Act: -0.0001

Data Index: 914172 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0298. Min Act: -0.0001

Data Index: 692977 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1199719 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0254. Min Act: -0.0001

Data Index: 843760 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0273. Min Act: -0.0001

Data Index: 1359079 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0280. Min Act: -0.0001

Data Index: 254009 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0286. Min Act: -0.0001

Data Index: 571800 (C4 (Web Text))

Max Activating Token Index: 397