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

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

Neuron 635 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0468. Min Range: -2.0468

Max Act: 2.0468. Min Act: -0.0000

Data Index: 444991 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.9385. Min Act: -0.0000

Data Index: 1286944 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.7062. Min Act: -0.0000

Data Index: 346044 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.5653. Min Act: -0.0000

Data Index: 438764 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.5553. Min Act: -0.0000

Data Index: 557838 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1329748 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.3084. Min Act: -0.0000

Data Index: 1196291 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1196953 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.2020. Min Act: -0.0000

Data Index: 419966 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.1949. Min Act: -0.0000

Data Index: 357759 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.1887. Min Act: -0.0000

Data Index: 236993 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.2175. Min Act: -0.0000

Data Index: 607921 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.1334. Min Act: -0.0000

Data Index: 102145 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.1643. Min Act: -0.0001

Data Index: 1078596 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.1359. Min Act: -0.0000

Data Index: 1088491 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.1540. Min Act: -0.0001

Data Index: 951667 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.1469. Min Act: -0.0000

Data Index: 100054 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.1379. Min Act: -0.0000

Data Index: 79946 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1160439 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 2.0468. Min Range: -2.0468

Max Act: 1.2441. Min Act: -0.0000

Data Index: 687954 (C4 (Web Text))

Max Activating Token Index: 635