Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3052 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.6565. Min Act: -0.0003

Data Index: 910761 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5826. Min Act: -0.0003

Data Index: 189585 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5812. Min Act: -0.0003

Data Index: 903459 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5549. Min Act: -0.0002

Data Index: 332105 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5737. Min Act: -0.0003

Data Index: 1110397 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5721. Min Act: -0.0003

Data Index: 19866 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5412. Min Act: -0.0002

Data Index: 891631 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5401. Min Act: -0.0003

Data Index: 1326462 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5128. Min Act: -0.0003

Data Index: 248880 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5305. Min Act: -0.0003

Data Index: 687634 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5293. Min Act: -0.0003

Data Index: 508565 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5222. Min Act: -0.0003

Data Index: 388036 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5159. Min Act: -0.0003

Data Index: 542185 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5083. Min Act: -0.0003

Data Index: 865912 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5105. Min Act: -0.0003

Data Index: 750782 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5229. Min Act: -0.0003

Data Index: 298935 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.5086. Min Act: -0.0003

Data Index: 1031190 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.4916. Min Act: -0.0002

Data Index: 1292231 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.4937. Min Act: -0.0003

Data Index: 1312337 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.6565. Min Range: -0.6565

Max Act: 0.4696. Min Act: -0.0002

Data Index: 1342442 (C4 (Web Text))

Max Activating Token Index: 29