Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1458 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.3046. Min Act: -0.0002

Data Index: 1232962 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2885. Min Act: -0.0002

Data Index: 1246669 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2949. Min Act: -0.0002

Data Index: 219306 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2874. Min Act: -0.0002

Data Index: 461814 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.3067. Min Act: -0.0002

Data Index: 745956 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2634. Min Act: -0.0002

Data Index: 1314105 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2638. Min Act: -0.0002

Data Index: 1320593 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2506. Min Act: -0.0002

Data Index: 1222272 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2726. Min Act: -0.0002

Data Index: 154860 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2540. Min Act: -0.0002

Data Index: 861154 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2747. Min Act: -0.0002

Data Index: 49712 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2846. Min Act: -0.0002

Data Index: 64447 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2730. Min Act: -0.0002

Data Index: 842167 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2631. Min Act: -0.0002

Data Index: 693390 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2925. Min Act: -0.0002

Data Index: 15159 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2633. Min Act: -0.0002

Data Index: 1077787 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2607. Min Act: -0.0002

Data Index: 1225139 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2807. Min Act: -0.0002

Data Index: 655315 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2360. Min Act: -0.0002

Data Index: 1137772 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2909. Min Act: -0.0002

Data Index: 1234066 (C4 (Web Text))

Max Activating Token Index: 691