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

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

Neuron 1542 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0628. Min Range: -1.0628

Max Act: 1.0362. Min Act: -0.0002

Data Index: 896686 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 1.0628. Min Range: -1.0628

Max Act: 1.0628. Min Act: -0.0002

Data Index: 955878 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9776. Min Act: -0.0002

Data Index: 683733 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9505. Min Act: -0.0002

Data Index: 876062 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9562. Min Act: -0.0002

Data Index: 264183 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 1.0628. Min Range: -1.0628

Max Act: 1.0181. Min Act: -0.0002

Data Index: 920055 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9701. Min Act: -0.0002

Data Index: 358455 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8101. Min Act: -0.0002

Data Index: 75464 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9025. Min Act: -0.0002

Data Index: 1111741 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9006. Min Act: -0.0002

Data Index: 1038650 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9007. Min Act: -0.0002

Data Index: 249413 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8052. Min Act: -0.0002

Data Index: 72785 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8266. Min Act: -0.0002

Data Index: 1005712 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8780. Min Act: -0.0002

Data Index: 1243083 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8617. Min Act: -0.0002

Data Index: 1324552 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9148. Min Act: -0.0002

Data Index: 233301 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8533. Min Act: -0.0002

Data Index: 1332108 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.7548. Min Act: -0.0002

Data Index: 793195 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8470. Min Act: -0.0002

Data Index: 328000 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8439. Min Act: -0.0002

Data Index: 1209333 (C4 (Web Text))

Max Activating Token Index: 58