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

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

Neuron 775 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: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1276012 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0573. Min Act: -0.0002

Data Index: 793660 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0529. Min Act: -0.0002

Data Index: 600681 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0505. Min Act: -0.0002

Data Index: 18898 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0506. Min Act: -0.0002

Data Index: 878187 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0487. Min Act: -0.0002

Data Index: 355164 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0506. Min Act: -0.0002

Data Index: 998519 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0499. Min Act: -0.0002

Data Index: 622342 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1211075 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0509. Min Act: -0.0002

Data Index: 956933 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0484. Min Act: -0.0002

Data Index: 97148 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0475. Min Act: -0.0002

Data Index: 670226 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1084303 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0503. Min Act: -0.0002

Data Index: 521085 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1220182 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0468. Min Act: -0.0002

Data Index: 833721 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0514. Min Act: -0.0002

Data Index: 422963 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0468. Min Act: -0.0002

Data Index: 508788 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1187644 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0483. Min Act: -0.0002

Data Index: 978423 (C4 (Web Text))

Max Activating Token Index: 429