Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2912 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2922. Min Act: -0.0001

Data Index: 1219017 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2530. Min Act: -0.0001

Data Index: 139369 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1269507 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2469. Min Act: -0.0001

Data Index: 871452 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2374. Min Act: -0.0001

Data Index: 680114 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2421. Min Act: -0.0001

Data Index: 653378 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2402. Min Act: -0.0001

Data Index: 519729 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2291. Min Act: -0.0001

Data Index: 1307960 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2341. Min Act: -0.0001

Data Index: 1104333 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2335. Min Act: -0.0001

Data Index: 297973 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2405. Min Act: -0.0001

Data Index: 951378 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2322. Min Act: -0.0001

Data Index: 65858 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2303. Min Act: -0.0001

Data Index: 187822 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2322. Min Act: -0.0001

Data Index: 659588 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2220. Min Act: -0.0001

Data Index: 373083 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2365. Min Act: -0.0001

Data Index: 231692 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2250. Min Act: -0.0001

Data Index: 781286 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2332. Min Act: -0.0001

Data Index: 1320640 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2237. Min Act: -0.0001

Data Index: 639277 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2209. Min Act: -0.0001

Data Index: 167813 (C4 (Web Text))

Max Activating Token Index: 778