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

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

Neuron 1148 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: 0.1672. Min Range: -0.1672

Max Act: 0.1577. Min Act: -0.0002

Data Index: 413540 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1566. Min Act: -0.0002

Data Index: 1050800 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1514. Min Act: -0.0002

Data Index: 475955 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1672. Min Act: -0.0002

Data Index: 410055 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1499. Min Act: -0.0002

Data Index: 696848 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1448. Min Act: -0.0002

Data Index: 1150698 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1414. Min Act: -0.0002

Data Index: 838156 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1580. Min Act: -0.0002

Data Index: 941110 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1488. Min Act: -0.0002

Data Index: 777551 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1644. Min Act: -0.0002

Data Index: 1044317 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1338. Min Act: -0.0002

Data Index: 356373 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1363. Min Act: -0.0002

Data Index: 845681 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1477. Min Act: -0.0002

Data Index: 626406 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1473. Min Act: -0.0002

Data Index: 44270 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1482. Min Act: -0.0002

Data Index: 895822 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1411. Min Act: -0.0002

Data Index: 214137 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1390. Min Act: -0.0002

Data Index: 346936 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1332. Min Act: -0.0002

Data Index: 1191629 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1325. Min Act: -0.0002

Data Index: 293546 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1182567 (C4 (Web Text))

Max Activating Token Index: 864