Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6074 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.4604. Min Act: -0.0002

Data Index: 1189686 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.3339. Min Act: -0.0003

Data Index: 692421 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2901. Min Act: -0.0002

Data Index: 84939 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2688. Min Act: -0.0002

Data Index: 1273371 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2735. Min Act: -0.0002

Data Index: 232450 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2268. Min Act: -0.0002

Data Index: 1280569 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2403. Min Act: -0.0002

Data Index: 818218 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2408. Min Act: -0.0002

Data Index: 399153 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1865. Min Act: -0.0003

Data Index: 289110 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1716. Min Act: -0.0002

Data Index: 538865 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1851. Min Act: -0.0002

Data Index: 640356 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1841. Min Act: -0.0002

Data Index: 644839 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1694. Min Act: -0.0002

Data Index: 273935 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1596. Min Act: -0.0002

Data Index: 56768 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1564. Min Act: -0.0002

Data Index: 735031 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1827. Min Act: -0.0002

Data Index: 27592 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1426. Min Act: -0.0002

Data Index: 1301099 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1649. Min Act: -0.0002

Data Index: 162396 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1496. Min Act: -0.0002

Data Index: 1193537 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1449. Min Act: -0.0002

Data Index: 1072080 (C4 (Web Text))

Max Activating Token Index: 867