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

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

Neuron 714 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.8265. Min Act: -0.0000

Data Index: 1234429 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.8385. Min Act: -0.0000

Data Index: 314037 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.7518. Min Act: 0.0001

Data Index: 1180541 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.7027. Min Act: -0.0000

Data Index: 352863 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.5259. Min Act: -0.0000

Data Index: 732574 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.5219. Min Act: -0.0000

Data Index: 1197984 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.6758. Min Act: -0.0000

Data Index: 745544 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.2473. Min Act: 0.0000

Data Index: 823808 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.4275. Min Act: -0.0000

Data Index: 1341106 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.1973. Min Act: -0.0000

Data Index: 1220822 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.1968. Min Act: -0.0000

Data Index: 936275 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.1987. Min Act: -0.0000

Data Index: 1080040 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.1548. Min Act: -0.0000

Data Index: 422653 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.1152. Min Act: -0.0000

Data Index: 276150 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.1087. Min Act: -0.0000

Data Index: 448510 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.2907. Min Act: -0.0000

Data Index: 1151977 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.2601. Min Act: -0.0000

Data Index: 190837 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.0445. Min Act: -0.0000

Data Index: 845978 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.0389. Min Act: -0.0000

Data Index: 765673 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 5.8385. Min Range: -5.8385

Max Act: 5.0163. Min Act: -0.0000

Data Index: 634977 (C4 (Web Text))

Max Activating Token Index: 198