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

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

Neuron 4581 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: 0.0756. Min Range: -0.0756

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1654076 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1369352 (Python Code)

Max Activating Token Index: 1020

Text #2

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1631864 (Python Code)

Max Activating Token Index: 633

Text #3

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1465246 (Python Code)

Max Activating Token Index: 991

Text #4

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1621467 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1396600 (Python Code)

Max Activating Token Index: 830

Text #6

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1550815 (Python Code)

Max Activating Token Index: 311

Text #7

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1473448 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1386393 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1655566 (Python Code)

Max Activating Token Index: 1012

Text #10

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1543590 (Python Code)

Max Activating Token Index: 654

Text #11

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1572040 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1554978 (Python Code)

Max Activating Token Index: 214

Text #13

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1496881 (Python Code)

Max Activating Token Index: 364

Text #14

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1440301 (Python Code)

Max Activating Token Index: 609

Text #15

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1366949 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1280164 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1604867 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1463061 (Python Code)

Max Activating Token Index: 917

Text #19

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1362018 (Python Code)

Max Activating Token Index: 21