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

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

Neuron 306 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.9123. Min Act: -0.0002

Data Index: 54324 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.8534. Min Act: -0.0002

Data Index: 116527 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.9832. Min Act: -0.0002

Data Index: 1144806 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.7797. Min Act: -0.0002

Data Index: 274949 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.9585. Min Act: -0.0002

Data Index: 1301226 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.8579. Min Act: -0.0002

Data Index: 396700 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.8065. Min Act: -0.0002

Data Index: 251404 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.8493. Min Act: -0.0001

Data Index: 1289325 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.9007. Min Act: -0.0001

Data Index: 342094 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.7356. Min Act: -0.0002

Data Index: 1018240 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.7786. Min Act: -0.0002

Data Index: 1081286 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.6831. Min Act: -0.0002

Data Index: 616703 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.7708. Min Act: -0.0002

Data Index: 914247 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.6767. Min Act: -0.0002

Data Index: 418279 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.7847. Min Act: -0.0002

Data Index: 630755 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.7801. Min Act: -0.0002

Data Index: 1250740 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.7806. Min Act: -0.0002

Data Index: 894227 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.7651. Min Act: -0.0002

Data Index: 668044 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.7605. Min Act: -0.0002

Data Index: 680818 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.9832. Min Range: -1.9832

Max Act: 1.7498. Min Act: -0.0001

Data Index: 419102 (C4 (Web Text))

Max Activating Token Index: 786