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

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

Neuron 4294 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0317. Min Range: -1.0317

Max Act: 1.0317. Min Act: -0.0000

Data Index: 910094 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8373. Min Act: -0.0000

Data Index: 106751 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8262. Min Act: -0.0000

Data Index: 642938 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7842. Min Act: -0.0000

Data Index: 993454 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1028422 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1333461 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1179472 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7191. Min Act: -0.0000

Data Index: 216562 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7691. Min Act: -0.0000

Data Index: 415189 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1044401 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7429. Min Act: -0.0000

Data Index: 915687 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7164. Min Act: -0.0000

Data Index: 125047 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1043826 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.6526. Min Act: -0.0000

Data Index: 285740 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.6287. Min Act: -0.0000

Data Index: 200124 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.6248. Min Act: -0.0000

Data Index: 600079 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.6251. Min Act: -0.0000

Data Index: 333123 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.6239. Min Act: 0.0000

Data Index: 838211 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.6368. Min Act: -0.0000

Data Index: 68515 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1105620 (C4 (Web Text))

Max Activating Token Index: 422