Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1072 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0825. Min Act: -0.0003

Data Index: 262677 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0812. Min Act: -0.0003

Data Index: 546773 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0725. Min Act: -0.0003

Data Index: 849315 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0645. Min Act: -0.0003

Data Index: 760706 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0706. Min Act: -0.0003

Data Index: 144941 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0679. Min Act: -0.0003

Data Index: 244203 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0650. Min Act: -0.0003

Data Index: 438879 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0658. Min Act: -0.0003

Data Index: 819734 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0609. Min Act: -0.0003

Data Index: 536862 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1129936 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0620. Min Act: -0.0003

Data Index: 428550 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0614. Min Act: -0.0003

Data Index: 81347 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1334117 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1250380 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0522. Min Act: -0.0003

Data Index: 552531 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0579. Min Act: -0.0003

Data Index: 454418 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0579. Min Act: -0.0003

Data Index: 760234 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1079441 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0501. Min Act: -0.0003

Data Index: 920199 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0518. Min Act: -0.0003

Data Index: 388664 (C4 (Web Text))

Max Activating Token Index: 571