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

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

Neuron 4083 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.7658. Min Act: -0.0000

Data Index: 913863 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6708. Min Act: -0.0000

Data Index: 166576 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1217648 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1344783 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6521. Min Act: -0.0000

Data Index: 921400 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1313925 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1013969 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6197. Min Act: -0.0000

Data Index: 637961 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6194. Min Act: -0.0000

Data Index: 32059 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6055. Min Act: -0.0000

Data Index: 622420 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6158. Min Act: -0.0000

Data Index: 21316 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6056. Min Act: -0.0000

Data Index: 604833 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6012. Min Act: -0.0000

Data Index: 681572 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6029. Min Act: -0.0000

Data Index: 895659 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6183. Min Act: -0.0000

Data Index: 241997 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6298. Min Act: -0.0000

Data Index: 6825 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.5901. Min Act: 0.0000

Data Index: 420859 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.6059. Min Act: -0.0000

Data Index: 832758 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.5846. Min Act: -0.0000

Data Index: 190683 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.7658. Min Range: -0.7658

Max Act: 0.5644. Min Act: -0.0000

Data Index: 575155 (C4 (Web Text))

Max Activating Token Index: 1021