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

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

Neuron 1906 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0715. Min Range: -1.0715

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1275896 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.9689. Min Act: -0.0000

Data Index: 344098 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.7687. Min Act: -0.0000

Data Index: 228034 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.7365. Min Act: -0.0000

Data Index: 158847 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.7237. Min Act: -0.0000

Data Index: 713453 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1256378 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.7159. Min Act: -0.0000

Data Index: 27409 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1650915 (Python Code)

Max Activating Token Index: 780

Text #8

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.6836. Min Act: -0.0000

Data Index: 763162 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.7272. Min Act: -0.0000

Data Index: 450303 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1285078 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.7206. Min Act: -0.0000

Data Index: 784118 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1550935 (Python Code)

Max Activating Token Index: 239

Text #13

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.6571. Min Act: -0.0000

Data Index: 636948 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.6513. Min Act: -0.0000

Data Index: 864087 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1414680 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1365662 (Python Code)

Max Activating Token Index: 951

Text #17

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1062401 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1642207 (Python Code)

Max Activating Token Index: 545

Text #19

Max Range: 1.0715. Min Range: -1.0715

Max Act: 0.6285. Min Act: -0.0000

Data Index: 270141 (C4 (Web Text))

Max Activating Token Index: 928