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

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

Neuron 3641 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: 0.0883. Min Range: -0.0883

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1116267 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0540. Min Act: -0.0002

Data Index: 344749 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0506. Min Act: -0.0002

Data Index: 375214 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0560. Min Act: -0.0002

Data Index: 375341 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0451. Min Act: -0.0002

Data Index: 702461 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0464. Min Act: -0.0002

Data Index: 832873 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0443. Min Act: -0.0002

Data Index: 605876 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1141980 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1287043 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0433. Min Act: -0.0002

Data Index: 612230 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0403. Min Act: -0.0002

Data Index: 701629 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0396. Min Act: -0.0002

Data Index: 217949 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1043603 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0368. Min Act: -0.0002

Data Index: 834712 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0419. Min Act: -0.0002

Data Index: 653336 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1593966 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1349717 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1168652 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0401. Min Act: -0.0002

Data Index: 740559 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0389. Min Act: -0.0002

Data Index: 409225 (C4 (Web Text))

Max Activating Token Index: 131