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

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

Neuron 1775 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: 0.0864. Min Range: -0.0864

Max Act: 0.0864. Min Act: -0.0002

Data Index: 349690 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0808. Min Act: -0.0002

Data Index: 518621 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1041282 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0677. Min Act: -0.0002

Data Index: 425766 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0637. Min Act: -0.0002

Data Index: 253018 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0650. Min Act: -0.0002

Data Index: 273881 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0623. Min Act: -0.0002

Data Index: 228481 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0656. Min Act: -0.0002

Data Index: 874963 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0624. Min Act: -0.0002

Data Index: 782930 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0636. Min Act: -0.0002

Data Index: 635942 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0634. Min Act: -0.0002

Data Index: 163915 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0645. Min Act: -0.0002

Data Index: 516647 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0626. Min Act: -0.0002

Data Index: 447573 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0613. Min Act: -0.0002

Data Index: 798442 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0618. Min Act: -0.0002

Data Index: 830309 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0619. Min Act: -0.0002

Data Index: 62576 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0629. Min Act: -0.0002

Data Index: 425662 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0605. Min Act: -0.0002

Data Index: 638027 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0601. Min Act: -0.0002

Data Index: 768462 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0618. Min Act: -0.0002

Data Index: 330374 (C4 (Web Text))

Max Activating Token Index: 761