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

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

Neuron 2783 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.9890. Min Act: -0.0001

Data Index: 1143110 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.9293. Min Act: -0.0001

Data Index: 601157 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8769. Min Act: -0.0001

Data Index: 290932 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.9329. Min Act: -0.0001

Data Index: 304416 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8630. Min Act: -0.0001

Data Index: 461529 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8924. Min Act: -0.0001

Data Index: 723732 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8053. Min Act: -0.0001

Data Index: 308410 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8747. Min Act: -0.0001

Data Index: 287249 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8247. Min Act: -0.0001

Data Index: 543574 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7868. Min Act: -0.0001

Data Index: 1293652 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8591. Min Act: -0.0001

Data Index: 77660 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8569. Min Act: -0.0001

Data Index: 355607 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8756. Min Act: -0.0001

Data Index: 292934 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8515. Min Act: -0.0001

Data Index: 471180 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7996. Min Act: -0.0001

Data Index: 389657 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8115. Min Act: -0.0001

Data Index: 387688 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8019. Min Act: -0.0001

Data Index: 130005 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8099. Min Act: -0.0001

Data Index: 38895 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7903. Min Act: -0.0001

Data Index: 825930 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7722. Min Act: -0.0001

Data Index: 1318295 (C4 (Web Text))

Max Activating Token Index: 97