Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 852 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0441. Min Act: -0.0002

Data Index: 553380 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0438. Min Act: -0.0002

Data Index: 721602 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0002

Data Index: 928549 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0434. Min Act: -0.0002

Data Index: 858047 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1032316 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0437. Min Act: -0.0002

Data Index: 238471 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0413. Min Act: -0.0002

Data Index: 790236 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0416. Min Act: -0.0002

Data Index: 527729 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0413. Min Act: -0.0002

Data Index: 861373 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0398. Min Act: -0.0002

Data Index: 603274 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0409. Min Act: -0.0002

Data Index: 575082 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0415. Min Act: -0.0002

Data Index: 940909 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0416. Min Act: -0.0002

Data Index: 946257 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0403. Min Act: -0.0002

Data Index: 558766 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1212950 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1308114 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1241729 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0379. Min Act: -0.0002

Data Index: 857341 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1104678 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0387. Min Act: -0.0002

Data Index: 473973 (C4 (Web Text))

Max Activating Token Index: 380