Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2824 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0724. Min Act: -0.0002

Data Index: 725656 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0656. Min Act: -0.0002

Data Index: 217149 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0581. Min Act: -0.0002

Data Index: 985597 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1069297 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1319231 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0498. Min Act: -0.0002

Data Index: 277798 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0479. Min Act: -0.0002

Data Index: 599076 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0466. Min Act: -0.0002

Data Index: 686826 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1100365 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0434. Min Act: -0.0002

Data Index: 234188 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0441. Min Act: -0.0002

Data Index: 250388 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1260632 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1214852 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1166729 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1319201 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1273802 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0394. Min Act: -0.0002

Data Index: 802575 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0377. Min Act: -0.0002

Data Index: 452177 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0373. Min Act: -0.0002

Data Index: 648032 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0354. Min Act: -0.0002

Data Index: 923997 (C4 (Web Text))

Max Activating Token Index: 878