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

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

Neuron 495 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.2092. Min Act: -0.0000

Data Index: 455022 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1721. Min Act: -0.0000

Data Index: 843379 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1190430 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1808. Min Act: -0.0000

Data Index: 296841 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1029755 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1308966 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1767. Min Act: -0.0000

Data Index: 853340 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1782. Min Act: -0.0000

Data Index: 101809 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1768. Min Act: -0.0000

Data Index: 221389 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1818. Min Act: -0.0000

Data Index: 496577 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1779. Min Act: -0.0000

Data Index: 582629 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1519. Min Act: -0.0000

Data Index: 335459 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1678. Min Act: -0.0000

Data Index: 832354 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1292898 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1638250 (Python Code)

Max Activating Token Index: 357

Text #15

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1618. Min Act: -0.0000

Data Index: 323438 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1491. Min Act: -0.0000

Data Index: 206593 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1420. Min Act: -0.0000

Data Index: 268700 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1563. Min Act: -0.0000

Data Index: 244368 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1349039 (C4 (Web Text))

Max Activating Token Index: 829