Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 820 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0707. Min Act: -0.0006

Data Index: 1415384 (Python Code)

Max Activating Token Index: 850

Text #1

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0696. Min Act: -0.0006

Data Index: 1467248 (Python Code)

Max Activating Token Index: 855

Text #2

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0626. Min Act: -0.0006

Data Index: 1643600 (Python Code)

Max Activating Token Index: 536

Text #3

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0599. Min Act: -0.0006

Data Index: 1626486 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0592. Min Act: -0.0006

Data Index: 820591 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0592. Min Act: -0.0005

Data Index: 1514547 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0565. Min Act: -0.0006

Data Index: 1499067 (Python Code)

Max Activating Token Index: 43

Text #7

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0573. Min Act: -0.0005

Data Index: 1560019 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0547. Min Act: -0.0006

Data Index: 1457436 (Python Code)

Max Activating Token Index: 357

Text #9

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0552. Min Act: -0.0005

Data Index: 1438364 (Python Code)

Max Activating Token Index: 229

Text #10

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0541. Min Act: -0.0006

Data Index: 1460806 (Python Code)

Max Activating Token Index: 189

Text #11

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0523. Min Act: -0.0005

Data Index: 1598301 (Python Code)

Max Activating Token Index: 1015

Text #12

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0531. Min Act: -0.0005

Data Index: 1454703 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0529. Min Act: -0.0006

Data Index: 1478247 (Python Code)

Max Activating Token Index: 578

Text #14

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0528. Min Act: -0.0006

Data Index: 1654113 (Python Code)

Max Activating Token Index: 105

Text #15

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0519. Min Act: -0.0006

Data Index: 1454092 (Python Code)

Max Activating Token Index: 848

Text #16

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0502. Min Act: -0.0006

Data Index: 1620877 (Python Code)

Max Activating Token Index: 642

Text #17

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0502. Min Act: -0.0006

Data Index: 1502898 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0520. Min Act: -0.0006

Data Index: 1552263 (Python Code)

Max Activating Token Index: 704

Text #19

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0510. Min Act: -0.0006

Data Index: 1621160 (Python Code)

Max Activating Token Index: 416