Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1167 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1469. Min Act: -0.0001

Data Index: 80906 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1548. Min Act: -0.0001

Data Index: 793231 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1448. Min Act: -0.0001

Data Index: 827114 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1388. Min Act: -0.0001

Data Index: 255688 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1483. Min Act: -0.0001

Data Index: 57736 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1468. Min Act: -0.0001

Data Index: 612692 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1408. Min Act: -0.0001

Data Index: 137618 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1210. Min Act: -0.0001

Data Index: 138194 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1437. Min Act: -0.0001

Data Index: 165955 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1112. Min Act: -0.0001

Data Index: 75049 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1282. Min Act: -0.0001

Data Index: 854924 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1340. Min Act: -0.0001

Data Index: 712633 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1299. Min Act: -0.0001

Data Index: 789694 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1176. Min Act: -0.0001

Data Index: 246099 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1224. Min Act: -0.0001

Data Index: 697475 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1230081 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1298. Min Act: -0.0001

Data Index: 471194 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1292. Min Act: -0.0001

Data Index: 833749 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1294. Min Act: -0.0001

Data Index: 475255 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1234. Min Act: -0.0001

Data Index: 881898 (C4 (Web Text))

Max Activating Token Index: 347