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

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

Neuron 1705 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: 1.1785. Min Range: -1.1785

Max Act: 1.1643. Min Act: -0.0000

Data Index: 406144 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.1785. Min Act: 0.0000

Data Index: 267122 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.1520. Min Act: -0.0000

Data Index: 625017 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.0949. Min Act: -0.0000

Data Index: 843354 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1127647 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9801. Min Act: -0.0000

Data Index: 330050 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8663. Min Act: -0.0000

Data Index: 642338 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.0329. Min Act: -0.0000

Data Index: 154087 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1330902 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9911. Min Act: -0.0000

Data Index: 615404 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1133422 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9363. Min Act: -0.0000

Data Index: 994124 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8515. Min Act: -0.0000

Data Index: 1010701 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1027432 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1138624 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9051. Min Act: -0.0000

Data Index: 603369 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9173. Min Act: -0.0000

Data Index: 590240 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8813. Min Act: -0.0000

Data Index: 271955 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1133488 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8727. Min Act: -0.0000

Data Index: 547618 (C4 (Web Text))

Max Activating Token Index: 524