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

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

Neuron 763 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8382. Min Range: -5.8382

Max Act: 5.6695. Min Act: -0.0000

Data Index: 1150078 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 5.8382. Min Range: -5.8382

Max Act: 5.8382. Min Act: -0.0000

Data Index: 578099 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.8948. Min Act: -0.0000

Data Index: 343214 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 5.8382. Min Range: -5.8382

Max Act: 5.0302. Min Act: -0.0000

Data Index: 1110467 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.9052. Min Act: -0.0000

Data Index: 1183270 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.5402. Min Act: -0.0000

Data Index: 1002493 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.5106. Min Act: -0.0000

Data Index: 859446 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.6357. Min Act: -0.0000

Data Index: 915711 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.4917. Min Act: -0.0000

Data Index: 252438 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.6393. Min Act: -0.0000

Data Index: 227599 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.1322. Min Act: -0.0000

Data Index: 555835 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.2805. Min Act: -0.0000

Data Index: 267862 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.3882. Min Act: -0.0000

Data Index: 1054724 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.7119. Min Act: -0.0000

Data Index: 424893 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.5330. Min Act: -0.0000

Data Index: 378838 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 5.8382. Min Range: -5.8382

Max Act: 3.9757. Min Act: -0.0000

Data Index: 939259 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.0791. Min Act: -0.0000

Data Index: 360122 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 5.8382. Min Range: -5.8382

Max Act: 3.8947. Min Act: -0.0000

Data Index: 1357682 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 5.8382. Min Range: -5.8382

Max Act: 4.0766. Min Act: -0.0000

Data Index: 908264 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 5.8382. Min Range: -5.8382

Max Act: 3.8417. Min Act: -0.0000

Data Index: 21577 (C4 (Web Text))

Max Activating Token Index: 861