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

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

Neuron 498 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1161560 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1359817 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1171594 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1071996 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1055317 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1343760 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0656. Min Act: -0.0001

Data Index: 358375 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1322254 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0581. Min Act: -0.0001

Data Index: 893806 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0645. Min Act: -0.0001

Data Index: 383900 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0572. Min Act: -0.0001

Data Index: 630788 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0637. Min Act: -0.0001

Data Index: 226818 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0629. Min Act: -0.0001

Data Index: 290757 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1117639 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0592. Min Act: -0.0001

Data Index: 977894 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0586. Min Act: -0.0001

Data Index: 745131 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0602. Min Act: -0.0001

Data Index: 186952 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0573. Min Act: -0.0001

Data Index: 53658 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0550. Min Act: -0.0001

Data Index: 429596 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0584. Min Act: -0.0001

Data Index: 147312 (C4 (Web Text))

Max Activating Token Index: 605