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

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

Neuron 3521 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1336654 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1044274 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.5029. Min Act: 0.0004

Data Index: 1311307 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.4811. Min Act: -0.0000

Data Index: 891239 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1341940 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1022490 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.4559. Min Act: 0.0000

Data Index: 886265 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.4671. Min Act: 0.0002

Data Index: 1009805 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.4350. Min Act: -0.0000

Data Index: 358389 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.4487. Min Act: 0.0001

Data Index: 359945 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.4206. Min Act: -0.0000

Data Index: 14744 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.4654. Min Act: 0.0000

Data Index: 893305 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.3999. Min Act: -0.0000

Data Index: 108559 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.3875. Min Act: -0.0000

Data Index: 485809 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.3691. Min Act: 0.0000

Data Index: 599275 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.4002. Min Act: -0.0000

Data Index: 691431 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.3902. Min Act: 0.0000

Data Index: 654709 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.3765. Min Act: -0.0000

Data Index: 348116 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.3656. Min Act: -0.0000

Data Index: 506597 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.6406. Min Range: -0.6406

Max Act: 0.3858. Min Act: 0.0001

Data Index: 1009709 (C4 (Web Text))

Max Activating Token Index: 495