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

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

Neuron 2508 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: 0.1285. Min Range: -0.1285

Max Act: 0.1285. Min Act: -0.0002

Data Index: 966189 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1099. Min Act: -0.0002

Data Index: 297278 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1110. Min Act: -0.0002

Data Index: 926214 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1142. Min Act: -0.0002

Data Index: 143573 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0947. Min Act: -0.0002

Data Index: 231232 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1491100 (Python Code)

Max Activating Token Index: 24

Text #6

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0921. Min Act: -0.0002

Data Index: 699637 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0889. Min Act: -0.0002

Data Index: 279039 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0892. Min Act: -0.0002

Data Index: 835316 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1400595 (Python Code)

Max Activating Token Index: 477

Text #10

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0868. Min Act: -0.0002

Data Index: 180900 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1229294 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1100974 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0846. Min Act: -0.0002

Data Index: 7581 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1541806 (Python Code)

Max Activating Token Index: 471

Text #15

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0837. Min Act: -0.0002

Data Index: 774996 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0803. Min Act: -0.0002

Data Index: 620808 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0806. Min Act: -0.0002

Data Index: 21261 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0864. Min Act: -0.0002

Data Index: 618044 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1422400 (Python Code)

Max Activating Token Index: 765