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

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

Neuron 4615 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.2234. Min Act: -0.0000

Data Index: 765306 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.0308. Min Act: -0.0000

Data Index: 86005 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9040. Min Act: -0.0000

Data Index: 265976 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8633. Min Act: -0.0000

Data Index: 760424 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1247613 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1148644 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1344593 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1153184 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8187. Min Act: -0.0000

Data Index: 146229 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7898. Min Act: -0.0001

Data Index: 1148296 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7908. Min Act: -0.0000

Data Index: 490447 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1032787 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8364. Min Act: -0.0000

Data Index: 283264 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8143. Min Act: -0.0000

Data Index: 203159 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7452. Min Act: -0.0000

Data Index: 322896 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7841. Min Act: -0.0000

Data Index: 684803 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7838. Min Act: -0.0000

Data Index: 1222571 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7614. Min Act: -0.0000

Data Index: 948935 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7868. Min Act: -0.0000

Data Index: 940208 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7795. Min Act: -0.0000

Data Index: 959336 (C4 (Web Text))

Max Activating Token Index: 55