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

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

Neuron 299 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.9864. Min Act: -0.0000

Data Index: 803973 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.7990. Min Act: -0.0000

Data Index: 201400 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.8987. Min Act: -0.0000

Data Index: 475712 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.8635. Min Act: -0.0000

Data Index: 1267581 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.6753. Min Act: -0.0000

Data Index: 728971 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.7715. Min Act: -0.0000

Data Index: 866981 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.6881. Min Act: -0.0000

Data Index: 1297960 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.6220. Min Act: -0.0000

Data Index: 908075 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.7879. Min Act: -0.0000

Data Index: 938783 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.7303. Min Act: -0.0000

Data Index: 441727 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.6254. Min Act: -0.0000

Data Index: 562510 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.5273. Min Act: -0.0000

Data Index: 244877 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.5567. Min Act: -0.0000

Data Index: 498726 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.4815. Min Act: -0.0000

Data Index: 1048689 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.4735. Min Act: -0.0000

Data Index: 1315493 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.5563. Min Act: -0.0000

Data Index: 1358250 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.5141. Min Act: -0.0000

Data Index: 1625039 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.4295. Min Act: -0.0000

Data Index: 686887 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.4172. Min Act: -0.0000

Data Index: 1261480 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 1.9864. Min Range: -1.9864

Max Act: 1.3821. Min Act: -0.0000

Data Index: 1538932 (Python Code)

Max Activating Token Index: 764