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

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

Neuron 1764 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: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0002

Data Index: 57264 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0515. Min Act: -0.0002

Data Index: 611469 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1257753 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0502. Min Act: -0.0002

Data Index: 217746 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0436. Min Act: -0.0002

Data Index: 536950 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0444. Min Act: -0.0002

Data Index: 959006 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0449. Min Act: -0.0002

Data Index: 313378 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1317628 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0406. Min Act: -0.0002

Data Index: 78956 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0435. Min Act: -0.0002

Data Index: 126265 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0465. Min Act: -0.0002

Data Index: 639256 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1355955 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1087534 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1240171 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1130899 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0408. Min Act: -0.0002

Data Index: 963396 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0422. Min Act: -0.0002

Data Index: 27846 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0397. Min Act: -0.0002

Data Index: 261730 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0384. Min Act: -0.0002

Data Index: 438156 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0434. Min Act: -0.0002

Data Index: 568096 (C4 (Web Text))

Max Activating Token Index: 741