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

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

Neuron 1024 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: 0.0537. Min Range: -0.0537

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1027130 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0527. Min Act: -0.0002

Data Index: 717810 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0532. Min Act: -0.0002

Data Index: 446070 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0537. Min Act: -0.0002

Data Index: 615483 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1076680 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0500. Min Act: -0.0002

Data Index: 853403 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1340506 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0454. Min Act: -0.0002

Data Index: 595707 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0473. Min Act: -0.0002

Data Index: 95638 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0436. Min Act: -0.0002

Data Index: 899713 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1052166 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0445. Min Act: -0.0002

Data Index: 144080 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0409. Min Act: -0.0002

Data Index: 556586 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1049262 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0477. Min Act: -0.0002

Data Index: 759562 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1165994 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1066447 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0412. Min Act: -0.0002

Data Index: 63972 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1353016 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0446. Min Act: -0.0002

Data Index: 520353 (C4 (Web Text))

Max Activating Token Index: 527