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

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

Neuron 3279 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0026. Min Act: -0.0002

Data Index: 848743 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0025. Min Act: -0.0002

Data Index: 131379 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0025. Min Act: -0.0002

Data Index: 242026 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1238742 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 1336417 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 740701 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 34070 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 397200 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 1085609 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 868204 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 383840 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 832067 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 821937 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 116448 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0023. Min Act: -0.0002

Data Index: 890471 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0023. Min Act: -0.0002

Data Index: 723414 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 1067780 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0023. Min Act: -0.0002

Data Index: 805968 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0023. Min Act: -0.0002

Data Index: 1231400 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0023. Min Act: -0.0002

Data Index: 1252833 (C4 (Web Text))

Max Activating Token Index: 380