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

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

Neuron 3543 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: 0.0491. Min Range: -0.0491

Max Act: 0.0491. Min Act: -0.0002

Data Index: 700347 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0479. Min Act: -0.0002

Data Index: 305698 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1016444 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0436. Min Act: -0.0003

Data Index: 911784 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0416. Min Act: -0.0002

Data Index: 98354 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1265908 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1061888 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0399. Min Act: -0.0002

Data Index: 787826 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1059326 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0394. Min Act: -0.0002

Data Index: 737990 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0364. Min Act: -0.0002

Data Index: 316531 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0358. Min Act: -0.0002

Data Index: 833616 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0358. Min Act: -0.0002

Data Index: 267034 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0360. Min Act: -0.0002

Data Index: 845097 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1057611 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1002858 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0346. Min Act: -0.0002

Data Index: 267576 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0342. Min Act: -0.0002

Data Index: 312026 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1081766 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0354. Min Act: -0.0002

Data Index: 748841 (C4 (Web Text))

Max Activating Token Index: 357