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

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

Neuron 2748 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.7334. Min Act: -0.0000

Data Index: 796027 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6646. Min Act: -0.0000

Data Index: 238876 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6141. Min Act: -0.0000

Data Index: 359345 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5782. Min Act: -0.0000

Data Index: 857229 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5201. Min Act: -0.0000

Data Index: 51250 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1019636 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1089437 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4727. Min Act: -0.0000

Data Index: 794387 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4308. Min Act: -0.0000

Data Index: 200791 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4227. Min Act: -0.0000

Data Index: 506043 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4202. Min Act: 0.0000

Data Index: 1347224 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4099. Min Act: -0.0000

Data Index: 800671 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4017. Min Act: -0.0000

Data Index: 166310 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4133. Min Act: -0.0000

Data Index: 863200 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1228325 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4153. Min Act: -0.0000

Data Index: 910394 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4282. Min Act: -0.0000

Data Index: 561223 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.4259. Min Act: -0.0000

Data Index: 846505 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.3949. Min Act: -0.0000

Data Index: 705587 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.3950. Min Act: -0.0000

Data Index: 627269 (C4 (Web Text))

Max Activating Token Index: 811