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

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

Neuron 5866 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.4219. Min Act: -0.0000

Data Index: 600439 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.5018. Min Act: -0.0000

Data Index: 526445 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.1436. Min Act: -0.0000

Data Index: 753961 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.2391. Min Act: -0.0000

Data Index: 1196899 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.3557. Min Act: -0.0000

Data Index: 857894 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.1675. Min Act: -0.0000

Data Index: 932610 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.2517. Min Act: -0.0000

Data Index: 141169 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.2270. Min Act: -0.0000

Data Index: 540958 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.1260. Min Act: -0.0000

Data Index: 316944 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 2.5018. Min Range: -2.5018

Max Act: 1.9891. Min Act: -0.0000

Data Index: 704353 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.0934. Min Act: -0.0000

Data Index: 893199 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.0927. Min Act: -0.0000

Data Index: 197353 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.0436. Min Act: -0.0000

Data Index: 504309 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.1553. Min Act: -0.0000

Data Index: 269031 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.0391. Min Act: -0.0000

Data Index: 353774 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.1387. Min Act: -0.0000

Data Index: 706440 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.1246. Min Act: -0.0000

Data Index: 115272 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 2.5018. Min Range: -2.5018

Max Act: 2.1159. Min Act: -0.0000

Data Index: 903256 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 2.5018. Min Range: -2.5018

Max Act: 1.8735. Min Act: -0.0000

Data Index: 1346829 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 2.5018. Min Range: -2.5018

Max Act: 1.8390. Min Act: -0.0000

Data Index: 1139508 (C4 (Web Text))

Max Activating Token Index: 32