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

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

Neuron 1772 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1506956 (Python Code)

Max Activating Token Index: 553

Text #1

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1626957 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1363252 (Python Code)

Max Activating Token Index: 668

Text #3

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1536993 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1526199 (Python Code)

Max Activating Token Index: 264

Text #5

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1478803 (Python Code)

Max Activating Token Index: 613

Text #6

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1621998 (Python Code)

Max Activating Token Index: 893

Text #7

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1365372 (Python Code)

Max Activating Token Index: 729

Text #8

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1384049 (Python Code)

Max Activating Token Index: 706

Text #9

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1630358 (Python Code)

Max Activating Token Index: 605

Text #10

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4115. Min Act: -0.0000

Data Index: 947904 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1595319 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1621968 (Python Code)

Max Activating Token Index: 594

Text #13

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1412201 (Python Code)

Max Activating Token Index: 759

Text #14

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1567661 (Python Code)

Max Activating Token Index: 460

Text #15

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1536288 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1476904 (Python Code)

Max Activating Token Index: 494

Text #17

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1603005 (Python Code)

Max Activating Token Index: 670

Text #18

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1556484 (Python Code)

Max Activating Token Index: 353

Text #19

Max Range: 0.5518. Min Range: -0.5518

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1604524 (Python Code)

Max Activating Token Index: 531