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

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

Neuron 5439 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.8847. Min Act: -0.0000

Data Index: 733674 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.6811. Min Act: -0.0000

Data Index: 1205032 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.5265. Min Act: -0.0000

Data Index: 1136127 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.6019. Min Act: -0.0000

Data Index: 825359 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.4915. Min Act: -0.0000

Data Index: 732798 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.3779. Min Act: -0.0000

Data Index: 628891 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.2270. Min Act: -0.0000

Data Index: 653351 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.3360. Min Act: -0.0000

Data Index: 1178311 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1053684 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.1207. Min Act: -0.0000

Data Index: 413928 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.2485. Min Act: -0.0000

Data Index: 650030 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.3039. Min Act: -0.0000

Data Index: 70534 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.2313. Min Act: -0.0000

Data Index: 1173527 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.1508. Min Act: -0.0000

Data Index: 1329833 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.1514. Min Act: -0.0000

Data Index: 616713 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.2138. Min Act: -0.0000

Data Index: 624448 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.1723. Min Act: -0.0000

Data Index: 582407 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.0921. Min Act: -0.0000

Data Index: 1357392 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.1688. Min Act: -0.0000

Data Index: 613310 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 1.8847. Min Range: -1.8847

Max Act: 1.1056. Min Act: -0.0000

Data Index: 636284 (C4 (Web Text))

Max Activating Token Index: 569