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

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

Neuron 3482 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1111148 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1184. Min Act: -0.0001

Data Index: 1251023 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1048. Min Act: -0.0001

Data Index: 325524 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0955. Min Act: -0.0001

Data Index: 739950 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1296734 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1188985 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0958. Min Act: -0.0001

Data Index: 734630 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0957. Min Act: -0.0001

Data Index: 292076 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0879. Min Act: -0.0001

Data Index: 120097 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0902. Min Act: -0.0001

Data Index: 206531 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0902. Min Act: -0.0001

Data Index: 761018 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0825. Min Act: -0.0001

Data Index: 342452 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0897. Min Act: -0.0001

Data Index: 567115 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1213960 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0860. Min Act: -0.0001

Data Index: 699977 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0818. Min Act: -0.0001

Data Index: 743752 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0838. Min Act: -0.0001

Data Index: 860829 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0813. Min Act: -0.0001

Data Index: 888573 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0836. Min Act: -0.0001

Data Index: 252058 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1121631 (C4 (Web Text))

Max Activating Token Index: 129