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

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

Neuron 542 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0002

Data Index: 272202 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0725. Min Act: -0.0002

Data Index: 380243 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0708. Min Act: -0.0002

Data Index: 889752 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0520. Min Act: -0.0002

Data Index: 764659 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0663. Min Act: -0.0002

Data Index: 873948 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0725. Min Act: -0.0002

Data Index: 154462 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0619. Min Act: -0.0002

Data Index: 272779 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0649. Min Act: -0.0002

Data Index: 250028 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1158647 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0604. Min Act: -0.0002

Data Index: 786978 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0595. Min Act: -0.0002

Data Index: 112101 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0613. Min Act: -0.0002

Data Index: 333901 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1020916 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0582. Min Act: -0.0002

Data Index: 19106 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0435. Min Act: -0.0002

Data Index: 783225 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0574. Min Act: -0.0002

Data Index: 512935 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1329735 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1178756 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0544. Min Act: -0.0002

Data Index: 562316 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0582. Min Act: -0.0002

Data Index: 403618 (C4 (Web Text))

Max Activating Token Index: 419