Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4022 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.5980. Min Act: -0.0000

Data Index: 1351834 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.2272. Min Act: -0.0000

Data Index: 53983 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.5255. Min Act: -0.0000

Data Index: 636640 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.2764. Min Act: -0.0000

Data Index: 712633 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.4097. Min Act: -0.0000

Data Index: 482563 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.4040. Min Act: -0.0000

Data Index: 1182821 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.4425. Min Act: -0.0000

Data Index: 411471 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.3607. Min Act: -0.0000

Data Index: 473163 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.2071. Min Act: -0.0000

Data Index: 347276 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.1141. Min Act: -0.0000

Data Index: 998487 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.2641. Min Act: -0.0000

Data Index: 95092 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 3.5980. Min Range: -3.5980

Max Act: 2.9492. Min Act: -0.0000

Data Index: 454170 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.1035. Min Act: -0.0000

Data Index: 868281 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.0934. Min Act: -0.0000

Data Index: 1013891 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 3.5980. Min Range: -3.5980

Max Act: 2.9774. Min Act: -0.0000

Data Index: 1340462 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 3.5980. Min Range: -3.5980

Max Act: 2.8200. Min Act: -0.0000

Data Index: 50865 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.1121. Min Act: -0.0000

Data Index: 206357 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 3.5980. Min Range: -3.5980

Max Act: 3.0937. Min Act: -0.0000

Data Index: 704523 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 3.5980. Min Range: -3.5980

Max Act: 2.9185. Min Act: -0.0000

Data Index: 23617 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 3.5980. Min Range: -3.5980

Max Act: 2.8830. Min Act: -0.0000

Data Index: 195686 (C4 (Web Text))

Max Activating Token Index: 378