Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 513 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0588. Min Act: -0.0002

Data Index: 642889 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0537. Min Act: -0.0002

Data Index: 994372 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0499. Min Act: -0.0002

Data Index: 153100 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0517. Min Act: -0.0002

Data Index: 834532 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1014176 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1111716 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0541. Min Act: -0.0002

Data Index: 117976 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1124435 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0526. Min Act: -0.0002

Data Index: 11386 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0497. Min Act: -0.0002

Data Index: 748678 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0497. Min Act: -0.0002

Data Index: 3026 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1131977 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0518. Min Act: -0.0002

Data Index: 735331 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1028766 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0507. Min Act: -0.0002

Data Index: 707363 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1428201 (Python Code)

Max Activating Token Index: 813

Text #16

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1256840 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1181320 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0504. Min Act: -0.0002

Data Index: 560359 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1204758 (C4 (Web Text))

Max Activating Token Index: 623