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

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

Neuron 145 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0695. Min Act: -0.0002

Data Index: 28444 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0002

Data Index: 349385 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0585. Min Act: -0.0002

Data Index: 808326 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1049786 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0577. Min Act: -0.0002

Data Index: 80550 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0549. Min Act: -0.0002

Data Index: 845975 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0546. Min Act: -0.0002

Data Index: 69348 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0545. Min Act: -0.0002

Data Index: 866813 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0520. Min Act: -0.0002

Data Index: 993268 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0524. Min Act: -0.0002

Data Index: 498203 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1297689 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0507. Min Act: -0.0002

Data Index: 410904 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0489. Min Act: -0.0002

Data Index: 172156 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1112509 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0503. Min Act: -0.0002

Data Index: 972547 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0503. Min Act: -0.0002

Data Index: 581631 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0517. Min Act: -0.0002

Data Index: 993572 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0485. Min Act: -0.0002

Data Index: 39027 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0518. Min Act: -0.0002

Data Index: 6219 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0503. Min Act: -0.0002

Data Index: 946207 (C4 (Web Text))

Max Activating Token Index: 165