Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 538 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2523. Min Act: -0.0001

Data Index: 646456 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1145203 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2074. Min Act: -0.0001

Data Index: 364881 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2021. Min Act: -0.0001

Data Index: 1060805 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2022. Min Act: -0.0001

Data Index: 928286 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1746. Min Act: -0.0001

Data Index: 1206578 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1796. Min Act: -0.0001

Data Index: 667266 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1124412 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1788. Min Act: -0.0001

Data Index: 292586 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1318615 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1829. Min Act: -0.0001

Data Index: 510431 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1791. Min Act: -0.0001

Data Index: 910098 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1745. Min Act: -0.0001

Data Index: 654437 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1725. Min Act: -0.0001

Data Index: 962122 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1735. Min Act: -0.0001

Data Index: 852550 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1268229 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1693. Min Act: -0.0001

Data Index: 221144 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1753. Min Act: -0.0001

Data Index: 755771 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1667. Min Act: -0.0001

Data Index: 684906 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1645. Min Act: -0.0001

Data Index: 815729 (C4 (Web Text))

Max Activating Token Index: 264