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

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

Neuron 48 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: 0.0972. Min Range: -0.0972

Max Act: 0.0972. Min Act: -0.0002

Data Index: 598661 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1065873 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0548. Min Act: -0.0002

Data Index: 246572 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0520. Min Act: -0.0002

Data Index: 783778 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0512. Min Act: -0.0002

Data Index: 218748 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0524. Min Act: -0.0002

Data Index: 374123 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1066543 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1182890 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1315613 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0458. Min Act: -0.0002

Data Index: 547150 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0466. Min Act: -0.0002

Data Index: 299400 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0463. Min Act: -0.0002

Data Index: 571318 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0451. Min Act: -0.0002

Data Index: 605265 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0459. Min Act: -0.0002

Data Index: 682785 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1218276 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0429. Min Act: -0.0002

Data Index: 872400 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0419. Min Act: -0.0002

Data Index: 804099 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0412. Min Act: -0.0002

Data Index: 369234 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1091800 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1345568 (C4 (Web Text))

Max Activating Token Index: 624