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

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

Neuron 355 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: 1.4768. Min Range: -1.4768

Max Act: 1.4768. Min Act: -0.0002

Data Index: 1522203 (Python Code)

Max Activating Token Index: 804

Text #1

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.3773. Min Act: -0.0002

Data Index: 1579171 (Python Code)

Max Activating Token Index: 715

Text #2

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.3405. Min Act: -0.0002

Data Index: 499417 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.3147. Min Act: -0.0002

Data Index: 1589642 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2788. Min Act: -0.0002

Data Index: 1627775 (Python Code)

Max Activating Token Index: 226

Text #5

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.3035. Min Act: -0.0002

Data Index: 1498666 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2391. Min Act: -0.0002

Data Index: 1650210 (Python Code)

Max Activating Token Index: 775

Text #7

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2614. Min Act: -0.0002

Data Index: 1432382 (Python Code)

Max Activating Token Index: 491

Text #8

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2412. Min Act: -0.0002

Data Index: 52431 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2262. Min Act: -0.0002

Data Index: 1537799 (Python Code)

Max Activating Token Index: 885

Text #10

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2068. Min Act: -0.0002

Data Index: 1421780 (Python Code)

Max Activating Token Index: 139

Text #11

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2416. Min Act: -0.0002

Data Index: 1503746 (Python Code)

Max Activating Token Index: 285

Text #12

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2511. Min Act: -0.0002

Data Index: 833231 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2439. Min Act: -0.0002

Data Index: 1448733 (Python Code)

Max Activating Token Index: 96

Text #14

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2204. Min Act: -0.0002

Data Index: 1638014 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2293. Min Act: -0.0002

Data Index: 1614303 (Python Code)

Max Activating Token Index: 148

Text #16

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2118. Min Act: -0.0002

Data Index: 1375804 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2209. Min Act: -0.0002

Data Index: 1525405 (Python Code)

Max Activating Token Index: 568

Text #18

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1696. Min Act: -0.0002

Data Index: 1604619 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1626. Min Act: -0.0002

Data Index: 1384188 (Python Code)

Max Activating Token Index: 534