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

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

Neuron 2384 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2147. Min Act: -0.0003

Data Index: 147121 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2200. Min Act: -0.0003

Data Index: 1287622 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1979. Min Act: -0.0003

Data Index: 216756 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1969. Min Act: -0.0003

Data Index: 192928 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1843. Min Act: -0.0003

Data Index: 1153096 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1791. Min Act: -0.0003

Data Index: 775157 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1807. Min Act: -0.0003

Data Index: 763365 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1668. Min Act: -0.0003

Data Index: 645089 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1661. Min Act: -0.0003

Data Index: 617068 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1597. Min Act: -0.0003

Data Index: 894966 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1704. Min Act: -0.0003

Data Index: 36001 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1631. Min Act: -0.0003

Data Index: 168083 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1602. Min Act: -0.0003

Data Index: 476349 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1592. Min Act: -0.0003

Data Index: 1138703 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1580. Min Act: -0.0003

Data Index: 1282046 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1565. Min Act: -0.0003

Data Index: 1137285 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1556. Min Act: -0.0003

Data Index: 422397 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1536. Min Act: -0.0003

Data Index: 326043 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1526. Min Act: -0.0003

Data Index: 1227862 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1511. Min Act: -0.0003

Data Index: 40755 (C4 (Web Text))

Max Activating Token Index: 845