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

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

Neuron 2432 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2530. Min Act: -0.0000

Data Index: 952294 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2238. Min Act: -0.0000

Data Index: 158936 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2111. Min Act: -0.0000

Data Index: 746314 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2161. Min Act: -0.0000

Data Index: 965596 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2124. Min Act: 0.0000

Data Index: 925343 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1954. Min Act: -0.0000

Data Index: 906091 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2056. Min Act: -0.0000

Data Index: 326994 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1216245 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1882. Min Act: -0.0000

Data Index: 174526 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1053988 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1975. Min Act: -0.0000

Data Index: 150771 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1958. Min Act: -0.0000

Data Index: 668718 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1851. Min Act: -0.0000

Data Index: 741727 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1841. Min Act: -0.0000

Data Index: 171994 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1806. Min Act: -0.0000

Data Index: 652202 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1826. Min Act: -0.0000

Data Index: 148454 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1761. Min Act: -0.0000

Data Index: 555170 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1341917 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1754. Min Act: -0.0000

Data Index: 554930 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1742. Min Act: -0.0000

Data Index: 980864 (C4 (Web Text))

Max Activating Token Index: 411