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

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

Neuron 3055 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: 0.1749. Min Range: -0.1749

Max Act: 0.1551. Min Act: -0.0002

Data Index: 1335722 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1749. Min Act: -0.0002

Data Index: 461194 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1629. Min Act: -0.0002

Data Index: 503952 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1613. Min Act: -0.0002

Data Index: 257279 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1520. Min Act: -0.0002

Data Index: 1264793 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1670. Min Act: -0.0002

Data Index: 1124882 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1529. Min Act: -0.0002

Data Index: 425946 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1503. Min Act: -0.0002

Data Index: 796869 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1524. Min Act: -0.0002

Data Index: 960908 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1528. Min Act: -0.0002

Data Index: 168863 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1500. Min Act: -0.0002

Data Index: 527322 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1446. Min Act: -0.0002

Data Index: 962532 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1358. Min Act: -0.0002

Data Index: 830116 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1429. Min Act: -0.0002

Data Index: 77201 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1436. Min Act: -0.0002

Data Index: 5555 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1554. Min Act: -0.0002

Data Index: 544128 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1373. Min Act: -0.0002

Data Index: 928670 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1409. Min Act: -0.0002

Data Index: 1286761 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1452. Min Act: -0.0002

Data Index: 958071 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1446. Min Act: -0.0002

Data Index: 819788 (C4 (Web Text))

Max Activating Token Index: 162