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

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

Neuron 5049 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.5980. Min Act: -0.0000

Data Index: 1192449 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.3720. Min Act: -0.0000

Data Index: 1061607 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.3617. Min Act: -0.0000

Data Index: 702680 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.2442. Min Act: -0.0000

Data Index: 289061 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.2424. Min Act: -0.0000

Data Index: 267685 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.2879. Min Act: -0.0000

Data Index: 126626 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1065749 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.2236. Min Act: -0.0000

Data Index: 427397 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1990. Min Act: -0.0000

Data Index: 465001 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1581. Min Act: -0.0000

Data Index: 736038 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1297167 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1201487 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1837. Min Act: -0.0000

Data Index: 855456 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1095. Min Act: -0.0000

Data Index: 972551 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1024. Min Act: -0.0000

Data Index: 14489 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1036275 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1023. Min Act: -0.0000

Data Index: 731395 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1696. Min Act: 0.0000

Data Index: 1094085 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0882. Min Act: -0.0000

Data Index: 1242878 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1023439 (C4 (Web Text))

Max Activating Token Index: 743