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

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

Neuron 2346 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3745. Min Act: 0.0000

Data Index: 628723 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3229. Min Act: -0.0000

Data Index: 343213 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1202817 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1099569 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3253. Min Act: -0.0001

Data Index: 1231275 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3301. Min Act: -0.0001

Data Index: 1579144 (Python Code)

Max Activating Token Index: 668

Text #6

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2906. Min Act: -0.0001

Data Index: 836346 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1198677 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2804. Min Act: -0.0001

Data Index: 171147 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2746. Min Act: -0.0001

Data Index: 536683 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2836. Min Act: -0.0001

Data Index: 691318 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2588. Min Act: -0.0001

Data Index: 312459 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2598. Min Act: 0.0000

Data Index: 653266 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2728. Min Act: -0.0000

Data Index: 536020 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2606. Min Act: -0.0001

Data Index: 1358683 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2506. Min Act: -0.0001

Data Index: 99925 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2677. Min Act: -0.0001

Data Index: 1083610 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2419. Min Act: -0.0000

Data Index: 962107 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2446. Min Act: -0.0001

Data Index: 979072 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2361. Min Act: -0.0001

Data Index: 1293309 (C4 (Web Text))

Max Activating Token Index: 842