Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 978 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1592507 (Python Code)

Max Activating Token Index: 437

Text #1

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1513890 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1518433 (Python Code)

Max Activating Token Index: 1003

Text #3

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1583367 (Python Code)

Max Activating Token Index: 999

Text #4

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1621216 (Python Code)

Max Activating Token Index: 603

Text #5

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1621267 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0440. Min Act: -0.0002

Data Index: 308371 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1588672 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0433. Min Act: -0.0002

Data Index: 294755 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1538710 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0436. Min Act: -0.0002

Data Index: 962640 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1372297 (Python Code)

Max Activating Token Index: 599

Text #12

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1615659 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1508882 (Python Code)

Max Activating Token Index: 564

Text #14

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1433191 (Python Code)

Max Activating Token Index: 272

Text #15

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1538376 (Python Code)

Max Activating Token Index: 343

Text #16

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0426. Min Act: -0.0002

Data Index: 852536 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1535779 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0420. Min Act: -0.0002

Data Index: 84140 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1109043 (C4 (Web Text))

Max Activating Token Index: 562