Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1249 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0434. Min Act: -0.0003

Data Index: 5714 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0433. Min Act: -0.0003

Data Index: 574409 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0457. Min Act: -0.0003

Data Index: 220603 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0429. Min Act: -0.0004

Data Index: 999245 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0423. Min Act: -0.0003

Data Index: 264009 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0401. Min Act: -0.0003

Data Index: 505200 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0417. Min Act: -0.0003

Data Index: 557920 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1012491 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0414. Min Act: -0.0003

Data Index: 241859 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0397. Min Act: -0.0003

Data Index: 873118 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1006581 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0374. Min Act: -0.0003

Data Index: 9611 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0400. Min Act: -0.0003

Data Index: 678652 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0368. Min Act: -0.0003

Data Index: 281868 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0405. Min Act: -0.0002

Data Index: 842991 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1058421 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0401. Min Act: -0.0003

Data Index: 57585 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0395. Min Act: -0.0003

Data Index: 865179 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0390. Min Act: -0.0003

Data Index: 997977 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0399. Min Act: -0.0003

Data Index: 51650 (C4 (Web Text))

Max Activating Token Index: 345