Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3056 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0893. Min Act: -0.0002

Data Index: 520243 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1245597 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0824. Min Act: -0.0001

Data Index: 311467 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0809. Min Act: -0.0002

Data Index: 762194 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1132797 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0779. Min Act: -0.0002

Data Index: 570722 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1058510 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1053294 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0697. Min Act: -0.0001

Data Index: 287114 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1187547 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0669. Min Act: -0.0001

Data Index: 429622 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0637. Min Act: -0.0002

Data Index: 736266 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0674. Min Act: -0.0002

Data Index: 569704 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0666. Min Act: -0.0002

Data Index: 488512 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1351431 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1058388 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0586. Min Act: -0.0002

Data Index: 257401 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1151251 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0650. Min Act: -0.0001

Data Index: 11404 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0620. Min Act: -0.0002

Data Index: 596803 (C4 (Web Text))

Max Activating Token Index: 270