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

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

Neuron 3842 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: 0.0849. Min Range: -0.0849

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1285850 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1126982 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0819. Min Act: -0.0002

Data Index: 795387 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0658. Min Act: -0.0002

Data Index: 173068 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0696. Min Act: -0.0002

Data Index: 96853 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0745. Min Act: -0.0002

Data Index: 544217 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0738. Min Act: -0.0002

Data Index: 852496 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0703. Min Act: -0.0003

Data Index: 173896 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0647. Min Act: -0.0002

Data Index: 580515 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0791. Min Act: -0.0002

Data Index: 454663 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0480. Min Act: -0.0002

Data Index: 547199 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0648. Min Act: -0.0002

Data Index: 546953 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0701. Min Act: -0.0002

Data Index: 703502 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1284239 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0712. Min Act: -0.0002

Data Index: 842464 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1022771 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0712. Min Act: -0.0002

Data Index: 719428 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0750. Min Act: -0.0002

Data Index: 706811 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0751. Min Act: -0.0002

Data Index: 494414 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0646. Min Act: -0.0002

Data Index: 612655 (C4 (Web Text))

Max Activating Token Index: 160