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

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

Neuron 793 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.2139. Min Act: -0.0000

Data Index: 600548 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1632290 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.2020. Min Act: -0.0000

Data Index: 718680 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1532560 (Python Code)

Max Activating Token Index: 888

Text #4

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1854. Min Act: -0.0000

Data Index: 374210 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1959. Min Act: -0.0000

Data Index: 786102 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1952. Min Act: -0.0000

Data Index: 374023 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1457194 (Python Code)

Max Activating Token Index: 102

Text #8

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1787. Min Act: -0.0000

Data Index: 641765 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1798. Min Act: -0.0000

Data Index: 998106 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1695. Min Act: -0.0000

Data Index: 479678 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1672. Min Act: -0.0000

Data Index: 614376 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1440045 (Python Code)

Max Activating Token Index: 983

Text #13

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1561. Min Act: -0.0000

Data Index: 667601 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1096767 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1657. Min Act: -0.0000

Data Index: 164110 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1734. Min Act: -0.0000

Data Index: 105841 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1493. Min Act: -0.0000

Data Index: 1252656 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1625. Min Act: -0.0000

Data Index: 586607 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1562. Min Act: -0.0000

Data Index: 504259 (C4 (Web Text))

Max Activating Token Index: 38