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

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

Neuron 3705 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: 0.0750. Min Range: -0.0750

Max Act: 0.0672. Min Act: -0.0002

Data Index: 812756 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0002

Data Index: 651402 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0714. Min Act: -0.0002

Data Index: 550815 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0675. Min Act: -0.0002

Data Index: 453495 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0700. Min Act: -0.0002

Data Index: 950196 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1138708 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0694. Min Act: -0.0002

Data Index: 31035 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0608. Min Act: -0.0002

Data Index: 180216 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0642. Min Act: -0.0002

Data Index: 59725 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1354257 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0659. Min Act: -0.0002

Data Index: 414522 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0595. Min Act: -0.0002

Data Index: 536533 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0658. Min Act: -0.0002

Data Index: 767078 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0609. Min Act: -0.0002

Data Index: 274075 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0663. Min Act: -0.0002

Data Index: 591639 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0569. Min Act: -0.0002

Data Index: 262650 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0601. Min Act: -0.0002

Data Index: 299600 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1082752 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1031817 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0578. Min Act: -0.0002

Data Index: 356914 (C4 (Web Text))

Max Activating Token Index: 332