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

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

Neuron 650 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: 0.0646. Min Range: -0.0646

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1222934 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0557. Min Act: -0.0002

Data Index: 588545 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0508. Min Act: -0.0002

Data Index: 348106 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0416. Min Act: -0.0002

Data Index: 401870 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0556. Min Act: -0.0002

Data Index: 916881 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0390. Min Act: -0.0002

Data Index: 548380 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0432. Min Act: -0.0002

Data Index: 7081 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0296. Min Act: -0.0002

Data Index: 214649 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1240692 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0484. Min Act: -0.0002

Data Index: 566412 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0582. Min Act: -0.0002

Data Index: 536149 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0455. Min Act: -0.0002

Data Index: 117691 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1201024 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0512. Min Act: -0.0002

Data Index: 158369 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1127871 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0543. Min Act: -0.0002

Data Index: 71108 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0487. Min Act: -0.0002

Data Index: 134910 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0498. Min Act: -0.0002

Data Index: 214170 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1391542 (Python Code)

Max Activating Token Index: 472

Text #19

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1539308 (Python Code)

Max Activating Token Index: 449