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

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

Neuron 5260 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: 0.0625. Min Range: -0.0625

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1006446 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0603. Min Act: -0.0002

Data Index: 701113 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1139895 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0510. Min Act: -0.0002

Data Index: 35354 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1039926 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0499. Min Act: -0.0002

Data Index: 419615 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0491. Min Act: -0.0002

Data Index: 877832 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1046072 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0448. Min Act: -0.0002

Data Index: 769012 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0465. Min Act: -0.0002

Data Index: 851548 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0458. Min Act: -0.0002

Data Index: 146577 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0454. Min Act: -0.0002

Data Index: 661311 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0435. Min Act: -0.0002

Data Index: 104495 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0418. Min Act: -0.0002

Data Index: 509610 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0432. Min Act: -0.0002

Data Index: 39512 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0433. Min Act: -0.0002

Data Index: 455937 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0445. Min Act: -0.0002

Data Index: 174156 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0447. Min Act: -0.0002

Data Index: 183906 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1236265 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0429. Min Act: -0.0002

Data Index: 404070 (C4 (Web Text))

Max Activating Token Index: 316