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

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

Neuron 638 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.5720. Min Act: -0.0001

Data Index: 190997 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.1350. Min Act: -0.0001

Data Index: 800510 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.2475. Min Act: -0.0001

Data Index: 737311 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.1192. Min Act: -0.0001

Data Index: 1191549 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 3.5720. Min Range: -3.5720

Max Act: 2.8520. Min Act: -0.0001

Data Index: 43746 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.0620. Min Act: -0.0001

Data Index: 52856 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.1519. Min Act: -0.0000

Data Index: 989169 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 3.5720. Min Range: -3.5720

Max Act: 2.8353. Min Act: -0.0001

Data Index: 113229 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 3.5720. Min Range: -3.5720

Max Act: 2.9688. Min Act: -0.0001

Data Index: 476031 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.2455. Min Act: -0.0001

Data Index: 1186434 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.0565. Min Act: -0.0001

Data Index: 42267 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 3.5720. Min Range: -3.5720

Max Act: 2.5134. Min Act: -0.0001

Data Index: 1031893 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.0325. Min Act: -0.0001

Data Index: 1110164 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 3.5720. Min Range: -3.5720

Max Act: 2.7476. Min Act: -0.0001

Data Index: 1307420 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 3.5720. Min Range: -3.5720

Max Act: 2.8873. Min Act: -0.0001

Data Index: 711997 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 3.5720. Min Range: -3.5720

Max Act: 2.5967. Min Act: -0.0001

Data Index: 1155158 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 3.5720. Min Range: -3.5720

Max Act: 2.6854. Min Act: -0.0001

Data Index: 1235597 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 3.5720. Min Range: -3.5720

Max Act: 2.8333. Min Act: -0.0001

Data Index: 1093530 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 3.5720. Min Range: -3.5720

Max Act: 2.8215. Min Act: -0.0000

Data Index: 271149 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 3.5720. Min Range: -3.5720

Max Act: 2.8055. Min Act: -0.0001

Data Index: 509957 (C4 (Web Text))

Max Activating Token Index: 587