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

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

Neuron 3082 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3704. Min Range: -2.3704

Max Act: 2.3013. Min Act: -0.0000

Data Index: 1624756 (Python Code)

Max Activating Token Index: 176

Text #1

Max Range: 2.3704. Min Range: -2.3704

Max Act: 2.3704. Min Act: -0.0000

Data Index: 1464721 (Python Code)

Max Activating Token Index: 745

Text #2

Max Range: 2.3704. Min Range: -2.3704

Max Act: 2.2715. Min Act: -0.0000

Data Index: 1633513 (Python Code)

Max Activating Token Index: 70

Text #3

Max Range: 2.3704. Min Range: -2.3704

Max Act: 2.1746. Min Act: -0.0000

Data Index: 1419266 (Python Code)

Max Activating Token Index: 633

Text #4

Max Range: 2.3704. Min Range: -2.3704

Max Act: 2.2262. Min Act: -0.0000

Data Index: 1483591 (Python Code)

Max Activating Token Index: 564

Text #5

Max Range: 2.3704. Min Range: -2.3704

Max Act: 2.1118. Min Act: -0.0000

Data Index: 1436992 (Python Code)

Max Activating Token Index: 135

Text #6

Max Range: 2.3704. Min Range: -2.3704

Max Act: 2.1971. Min Act: -0.0000

Data Index: 1491484 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 2.3704. Min Range: -2.3704

Max Act: 2.0437. Min Act: -0.0000

Data Index: 1594710 (Python Code)

Max Activating Token Index: 782

Text #8

Max Range: 2.3704. Min Range: -2.3704

Max Act: 2.0190. Min Act: -0.0000

Data Index: 1484476 (Python Code)

Max Activating Token Index: 369

Text #9

Max Range: 2.3704. Min Range: -2.3704

Max Act: 1.9613. Min Act: -0.0000

Data Index: 1516819 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 2.3704. Min Range: -2.3704

Max Act: 2.0810. Min Act: -0.0000

Data Index: 1420645 (Python Code)

Max Activating Token Index: 110

Text #11

Max Range: 2.3704. Min Range: -2.3704

Max Act: 2.0459. Min Act: -0.0000

Data Index: 1524988 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 2.3704. Min Range: -2.3704

Max Act: 1.8650. Min Act: -0.0000

Data Index: 1504373 (Python Code)

Max Activating Token Index: 203

Text #13

Max Range: 2.3704. Min Range: -2.3704

Max Act: 1.9878. Min Act: -0.0000

Data Index: 1656485 (Python Code)

Max Activating Token Index: 285

Text #14

Max Range: 2.3704. Min Range: -2.3704

Max Act: 1.8967. Min Act: -0.0000

Data Index: 1379170 (Python Code)

Max Activating Token Index: 735

Text #15

Max Range: 2.3704. Min Range: -2.3704

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1555020 (Python Code)

Max Activating Token Index: 541

Text #16

Max Range: 2.3704. Min Range: -2.3704

Max Act: 1.8055. Min Act: -0.0000

Data Index: 1521722 (Python Code)

Max Activating Token Index: 812

Text #17

Max Range: 2.3704. Min Range: -2.3704

Max Act: 1.7505. Min Act: -0.0000

Data Index: 1500477 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 2.3704. Min Range: -2.3704

Max Act: 1.7302. Min Act: -0.0000

Data Index: 113679 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 2.3704. Min Range: -2.3704

Max Act: 1.7488. Min Act: -0.0000

Data Index: 1453416 (Python Code)

Max Activating Token Index: 352