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

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

Neuron 3946 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: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0002

Data Index: 984727 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0475. Min Act: -0.0002

Data Index: 294956 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0468. Min Act: -0.0002

Data Index: 231730 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0483. Min Act: -0.0002

Data Index: 769508 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0454. Min Act: -0.0002

Data Index: 772536 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0424. Min Act: -0.0002

Data Index: 960268 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0480. Min Act: -0.0002

Data Index: 212199 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0445. Min Act: -0.0002

Data Index: 171302 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1217397 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0475. Min Act: -0.0002

Data Index: 685371 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0421. Min Act: -0.0002

Data Index: 153992 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0453. Min Act: -0.0002

Data Index: 184330 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1053949 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0464. Min Act: -0.0002

Data Index: 382298 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1430578 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0434. Min Act: -0.0002

Data Index: 113520 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1135360 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0419. Min Act: -0.0002

Data Index: 92294 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0413. Min Act: -0.0002

Data Index: 114400 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0417. Min Act: -0.0002

Data Index: 324755 (C4 (Web Text))

Max Activating Token Index: 400