Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 763 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1568. Min Act: -0.0002

Data Index: 290273 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1558. Min Act: -0.0001

Data Index: 600357 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1318. Min Act: -0.0002

Data Index: 72385 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1467. Min Act: -0.0001

Data Index: 809430 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1426. Min Act: -0.0002

Data Index: 579096 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.0290. Min Act: -0.0001

Data Index: 637808 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1504. Min Act: -0.0002

Data Index: 997359 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.0890. Min Act: -0.0002

Data Index: 138680 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1192. Min Act: -0.0001

Data Index: 43929 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1374. Min Act: -0.0002

Data Index: 359153 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.0095. Min Act: -0.0002

Data Index: 465602 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1201427 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1495. Min Act: -0.0002

Data Index: 1354416 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1164. Min Act: -0.0002

Data Index: 626498 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1312. Min Act: -0.0002

Data Index: 797428 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1306. Min Act: -0.0002

Data Index: 792076 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1046. Min Act: -0.0002

Data Index: 59381 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1225. Min Act: -0.0001

Data Index: 875188 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1232385 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.0187. Min Act: -0.0002

Data Index: 695966 (C4 (Web Text))

Max Activating Token Index: 643