Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 824 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0004

Data Index: 1365833 (Python Code)

Max Activating Token Index: 633

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0788. Min Act: -0.0004

Data Index: 1648201 (Python Code)

Max Activating Token Index: 269

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0646. Min Act: -0.0004

Data Index: 1615505 (Python Code)

Max Activating Token Index: 541

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0611. Min Act: -0.0004

Data Index: 1407902 (Python Code)

Max Activating Token Index: 1020

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0585. Min Act: -0.0004

Data Index: 1414974 (Python Code)

Max Activating Token Index: 492

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0511. Min Act: -0.0004

Data Index: 1398777 (Python Code)

Max Activating Token Index: 666

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0508. Min Act: -0.0004

Data Index: 1531990 (Python Code)

Max Activating Token Index: 735

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0466. Min Act: -0.0004

Data Index: 1529340 (Python Code)

Max Activating Token Index: 521

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1497553 (Python Code)

Max Activating Token Index: 80

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0443. Min Act: -0.0004

Data Index: 1374245 (Python Code)

Max Activating Token Index: 367

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0415. Min Act: -0.0004

Data Index: 1360732 (Python Code)

Max Activating Token Index: 386

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0412. Min Act: -0.0004

Data Index: 1518804 (Python Code)

Max Activating Token Index: 992

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0405. Min Act: -0.0004

Data Index: 1496281 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0389. Min Act: -0.0004

Data Index: 1583177 (Python Code)

Max Activating Token Index: 827

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0393. Min Act: -0.0004

Data Index: 1398109 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0390. Min Act: -0.0004

Data Index: 1577046 (Python Code)

Max Activating Token Index: 238

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1505522 (Python Code)

Max Activating Token Index: 763

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0394. Min Act: -0.0004

Data Index: 1383106 (Python Code)

Max Activating Token Index: 899

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0382. Min Act: -0.0004

Data Index: 1421112 (Python Code)

Max Activating Token Index: 588

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0381. Min Act: -0.0004

Data Index: 1577049 (Python Code)

Max Activating Token Index: 279