Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3827 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2246. Min Act: -0.0001

Data Index: 548679 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2235. Min Act: -0.0001

Data Index: 664569 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2016. Min Act: -0.0001

Data Index: 645623 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1896. Min Act: -0.0002

Data Index: 192883 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1873. Min Act: -0.0002

Data Index: 25534 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1855. Min Act: -0.0002

Data Index: 660412 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1805. Min Act: -0.0001

Data Index: 137553 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1803. Min Act: -0.0001

Data Index: 555152 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1744. Min Act: -0.0001

Data Index: 603906 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1789. Min Act: -0.0002

Data Index: 433933 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1792. Min Act: -0.0002

Data Index: 1128085 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1759. Min Act: -0.0001

Data Index: 40089 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1755. Min Act: -0.0002

Data Index: 766802 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1697. Min Act: -0.0002

Data Index: 626804 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1758. Min Act: -0.0002

Data Index: 669074 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1663. Min Act: -0.0001

Data Index: 519011 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1726. Min Act: -0.0001

Data Index: 1144444 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1764. Min Act: -0.0002

Data Index: 1302379 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1530. Min Act: -0.0002

Data Index: 287725 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1683. Min Act: -0.0001

Data Index: 752748 (C4 (Web Text))

Max Activating Token Index: 674