Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 16 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.4824. Min Act: -0.0002

Data Index: 604768 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.3606. Min Act: -0.0002

Data Index: 814235 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.2351. Min Act: -0.0001

Data Index: 591161 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.1025. Min Act: -0.0002

Data Index: 720461 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.1460. Min Act: -0.0002

Data Index: 431605 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.0888. Min Act: -0.0002

Data Index: 1040148 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.1687. Min Act: -0.0002

Data Index: 730409 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.3800. Min Act: -0.0002

Data Index: 737264 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.2019. Min Act: -0.0002

Data Index: 679661 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.0549. Min Act: -0.0002

Data Index: 857971 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.1033. Min Act: -0.0002

Data Index: 1040582 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.0931. Min Act: -0.0002

Data Index: 1353895 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.0899. Min Act: -0.0002

Data Index: 6242 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.1226. Min Act: -0.0002

Data Index: 719733 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.2110. Min Act: -0.0001

Data Index: 1259822 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.0501. Min Act: -0.0002

Data Index: 826701 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.1226. Min Act: -0.0002

Data Index: 443426 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.0222. Min Act: -0.0002

Data Index: 299572 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 1.4824. Min Range: -1.4824

Max Act: 1.0127. Min Act: -0.0002

Data Index: 470186 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 1.4824. Min Range: -1.4824

Max Act: 0.9357. Min Act: -0.0002

Data Index: 323171 (C4 (Web Text))

Max Activating Token Index: 654