Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1878 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1638590 (Python Code)

Max Activating Token Index: 854

Text #1

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0482. Min Act: -0.0003

Data Index: 888480 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1558400 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1624504 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1091986 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1561604 (Python Code)

Max Activating Token Index: 852

Text #6

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1428425 (Python Code)

Max Activating Token Index: 908

Text #7

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1432057 (Python Code)

Max Activating Token Index: 946

Text #8

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0473. Min Act: -0.0004

Data Index: 475224 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1468277 (Python Code)

Max Activating Token Index: 851

Text #10

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1381544 (Python Code)

Max Activating Token Index: 928

Text #11

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1499275 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0443. Min Act: -0.0003

Data Index: 620621 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1610510 (Python Code)

Max Activating Token Index: 503

Text #14

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0411. Min Act: -0.0003

Data Index: 1525930 (Python Code)

Max Activating Token Index: 691

Text #15

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1539995 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1473488 (Python Code)

Max Activating Token Index: 1006

Text #17

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0419. Min Act: -0.0003

Data Index: 249377 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1423326 (Python Code)

Max Activating Token Index: 902

Text #19

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1512485 (Python Code)

Max Activating Token Index: 509