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

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

Neuron 515 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: 1.1220. Min Range: -1.1220

Max Act: 1.1220. Min Act: -0.0000

Data Index: 984995 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0850. Min Act: -0.0000

Data Index: 541958 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0281. Min Act: -0.0000

Data Index: 932677 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1103991 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9824. Min Act: -0.0000

Data Index: 883287 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9757. Min Act: -0.0000

Data Index: 639544 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1055710 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8658. Min Act: -0.0000

Data Index: 137142 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8605. Min Act: -0.0000

Data Index: 942191 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8970. Min Act: -0.0000

Data Index: 270191 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1216803 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8561. Min Act: -0.0000

Data Index: 871730 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8115. Min Act: -0.0000

Data Index: 372107 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8557. Min Act: -0.0000

Data Index: 283976 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7590. Min Act: -0.0000

Data Index: 483313 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7604. Min Act: -0.0000

Data Index: 883659 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7716. Min Act: -0.0000

Data Index: 579819 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7681. Min Act: -0.0000

Data Index: 794614 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7945. Min Act: -0.0000

Data Index: 361014 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7268. Min Act: -0.0000

Data Index: 629781 (C4 (Web Text))

Max Activating Token Index: 909