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

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

Neuron 3328 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0727. Min Act: -0.0002

Data Index: 669874 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0655. Min Act: -0.0002

Data Index: 579783 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0665. Min Act: -0.0002

Data Index: 358453 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0628. Min Act: -0.0002

Data Index: 668006 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1168389 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0564. Min Act: -0.0002

Data Index: 816139 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0580. Min Act: -0.0002

Data Index: 433510 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0547. Min Act: -0.0002

Data Index: 662975 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1256558 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1017015 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0515. Min Act: -0.0002

Data Index: 568662 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0515. Min Act: -0.0002

Data Index: 442738 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0502. Min Act: -0.0002

Data Index: 507452 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1218466 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0496. Min Act: -0.0002

Data Index: 553247 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0477. Min Act: -0.0002

Data Index: 491690 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1255255 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0454. Min Act: -0.0002

Data Index: 546845 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0455. Min Act: -0.0002

Data Index: 517480 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1091169 (C4 (Web Text))

Max Activating Token Index: 707