Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1423. Min Range: -1.1423

Max Act: 1.1423. Min Act: -0.0000

Data Index: 684470 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1817729 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1458319 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1086311 (The Pile)

Max Activating Token Index: 957

Text #4

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8122. Min Act: -0.0000

Data Index: 693196 (The Pile)

Max Activating Token Index: 314

Text #5

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7908. Min Act: -0.0000

Data Index: 790190 (The Pile)

Max Activating Token Index: 190

Text #6

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7709. Min Act: -0.0000

Data Index: 916789 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8012. Min Act: -0.0000

Data Index: 722696 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1178108 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1091361 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7031. Min Act: -0.0000

Data Index: 777481 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1294590 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.6296. Min Act: -0.0000

Data Index: 819927 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7189. Min Act: -0.0000

Data Index: 913120 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.6768. Min Act: -0.0000

Data Index: 534515 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1290636 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1623763 (The Pile)

Max Activating Token Index: 613

Text #17

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.6608. Min Act: -0.0000

Data Index: 300653 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.6215. Min Act: -0.0000

Data Index: 218450 (The Pile)

Max Activating Token Index: 348

Text #19

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1637831 (The Pile)

Max Activating Token Index: 476