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

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

Neuron 2739 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1360. Min Range: -1.1360

Max Act: 1.1360. Min Act: -0.0000

Data Index: 102277 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.1360. Min Range: -1.1360

Max Act: 1.0164. Min Act: -0.0000

Data Index: 192294 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 1.1360. Min Range: -1.1360

Max Act: 1.0071. Min Act: -0.0000

Data Index: 247434 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8782. Min Act: -0.0000

Data Index: 569921 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1492 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.7580. Min Act: -0.0000

Data Index: 891415 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8674. Min Act: -0.0000

Data Index: 846103 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8649. Min Act: -0.0000

Data Index: 117216 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8781. Min Act: -0.0000

Data Index: 887195 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8931. Min Act: -0.0000

Data Index: 94503 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8440. Min Act: -0.0000

Data Index: 888649 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1191772 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1060924 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.9025. Min Act: -0.0000

Data Index: 103517 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8429. Min Act: -0.0000

Data Index: 23588 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1123988 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.8325. Min Act: -0.0000

Data Index: 160897 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.7637. Min Act: -0.0000

Data Index: 403307 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.7329. Min Act: -0.0000

Data Index: 247609 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 1.1360. Min Range: -1.1360

Max Act: 0.7318. Min Act: -0.0000

Data Index: 727399 (C4 (Web Text))

Max Activating Token Index: 896