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

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

Neuron 4569 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: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1031571 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0564. Min Act: -0.0002

Data Index: 155668 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0471. Min Act: -0.0002

Data Index: 189594 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1356812 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1348505 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0469. Min Act: -0.0002

Data Index: 529250 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1197273 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1280719 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0415. Min Act: -0.0002

Data Index: 810952 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0432. Min Act: -0.0002

Data Index: 271932 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0404. Min Act: -0.0002

Data Index: 680119 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0414. Min Act: -0.0002

Data Index: 302965 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0424. Min Act: -0.0002

Data Index: 678993 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0415. Min Act: -0.0002

Data Index: 312993 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1200364 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0361. Min Act: -0.0002

Data Index: 795975 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0416. Min Act: -0.0002

Data Index: 575225 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1007829 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0414. Min Act: -0.0002

Data Index: 560899 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0382. Min Act: -0.0002

Data Index: 500668 (C4 (Web Text))

Max Activating Token Index: 125