Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1588 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1314145 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2307. Min Act: -0.0000

Data Index: 10258 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1141985 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1074846 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1312813 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1972. Min Act: -0.0000

Data Index: 902215 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1556807 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1359823 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1938. Min Act: -0.0001

Data Index: 1132923 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1921. Min Act: -0.0000

Data Index: 395946 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1891. Min Act: -0.0001

Data Index: 763726 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1828. Min Act: -0.0001

Data Index: 1656225 (Python Code)

Max Activating Token Index: 713

Text #12

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1815. Min Act: -0.0000

Data Index: 605053 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1666. Min Act: -0.0000

Data Index: 512697 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1494206 (Python Code)

Max Activating Token Index: 613

Text #15

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1014922 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1649. Min Act: -0.0001

Data Index: 1000204 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1633. Min Act: -0.0000

Data Index: 666276 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1639. Min Act: -0.0000

Data Index: 830497 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1575. Min Act: -0.0000

Data Index: 344173 (C4 (Web Text))

Max Activating Token Index: 445