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

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

Neuron 1128 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1038994 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.3415. Min Act: -0.0000

Data Index: 927867 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.2913. Min Act: -0.0000

Data Index: 448880 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1515308 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.2079. Min Act: -0.0000

Data Index: 358241 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1026316 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.1403. Min Act: -0.0000

Data Index: 654174 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1038291 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.1298. Min Act: -0.0000

Data Index: 1048864 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.1440. Min Act: -0.0000

Data Index: 771812 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.0446. Min Act: -0.0000

Data Index: 382590 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.0635. Min Act: -0.0000

Data Index: 843342 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1644322 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.0260. Min Act: -0.0000

Data Index: 373666 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1311610 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.3415. Min Range: -1.3415

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1286629 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.0607. Min Act: -0.0000

Data Index: 158263 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 1.3415. Min Range: -1.3415

Max Act: 1.0367. Min Act: -0.0000

Data Index: 1306940 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.3415. Min Range: -1.3415

Max Act: 0.9557. Min Act: -0.0000

Data Index: 883916 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 1.3415. Min Range: -1.3415

Max Act: 0.9266. Min Act: -0.0000

Data Index: 708272 (C4 (Web Text))

Max Activating Token Index: 849