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

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

Neuron 1096 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: 1.6654. Min Range: -1.6654

Max Act: 1.6654. Min Act: -0.0001

Data Index: 945186 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.5287. Min Act: -0.0001

Data Index: 17616 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.3357. Min Act: -0.0002

Data Index: 633692 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.3919. Min Act: -0.0001

Data Index: 885053 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.4658. Min Act: -0.0002

Data Index: 441678 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.3509. Min Act: -0.0002

Data Index: 260123 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.2284. Min Act: -0.0001

Data Index: 960020 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.3122. Min Act: -0.0001

Data Index: 231230 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.4112. Min Act: -0.0001

Data Index: 340851 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.2940. Min Act: -0.0002

Data Index: 1212368 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.1191. Min Act: -0.0001

Data Index: 580881 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.2198. Min Act: -0.0001

Data Index: 606055 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.1136. Min Act: -0.0001

Data Index: 301992 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.1930. Min Act: -0.0001

Data Index: 518162 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.0984. Min Act: -0.0002

Data Index: 1320318 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.2176. Min Act: -0.0001

Data Index: 647069 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.1950. Min Act: -0.0001

Data Index: 585790 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.2842. Min Act: -0.0002

Data Index: 1286850 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.0090. Min Act: -0.0001

Data Index: 814364 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 1.6654. Min Range: -1.6654

Max Act: 1.2172. Min Act: -0.0001

Data Index: 1262668 (C4 (Web Text))

Max Activating Token Index: 221