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

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

Neuron 1737 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.6240. Min Act: -0.0000

Data Index: 858397 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1078014 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1476017 (Python Code)

Max Activating Token Index: 437

Text #3

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.6240. Min Act: -0.0000

Data Index: 915956 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5071. Min Act: -0.0000

Data Index: 683832 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1232969 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5210. Min Act: -0.0000

Data Index: 415353 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1444508 (Python Code)

Max Activating Token Index: 1000

Text #8

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5582. Min Act: -0.0001

Data Index: 584869 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1060356 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1575737 (Python Code)

Max Activating Token Index: 966

Text #11

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5267. Min Act: -0.0000

Data Index: 372401 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5252. Min Act: -0.0000

Data Index: 243802 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1261419 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4850. Min Act: -0.0000

Data Index: 193415 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5137. Min Act: -0.0000

Data Index: 809546 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5281. Min Act: -0.0000

Data Index: 244864 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4916. Min Act: -0.0000

Data Index: 930868 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4734. Min Act: -0.0000

Data Index: 16065 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5153. Min Act: -0.0000

Data Index: 368842 (C4 (Web Text))

Max Activating Token Index: 680