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

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

Neuron 2450 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: 0.9094. Min Range: -0.9094

Max Act: 0.9094. Min Act: -0.0000

Data Index: 586751 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7514. Min Act: -0.0000

Data Index: 834544 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7165. Min Act: -0.0000

Data Index: 526605 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7044. Min Act: -0.0000

Data Index: 969995 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6683. Min Act: -0.0000

Data Index: 650877 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6643. Min Act: -0.0000

Data Index: 830862 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6315. Min Act: -0.0000

Data Index: 253572 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1175154 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5953. Min Act: -0.0000

Data Index: 300098 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5225. Min Act: -0.0000

Data Index: 606255 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5771. Min Act: -0.0000

Data Index: 671546 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5730. Min Act: -0.0000

Data Index: 806101 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5850. Min Act: -0.0000

Data Index: 851512 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5689. Min Act: -0.0000

Data Index: 958376 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5824. Min Act: -0.0000

Data Index: 202210 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5774. Min Act: -0.0000

Data Index: 672874 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6301. Min Act: -0.0000

Data Index: 318322 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5279. Min Act: -0.0000

Data Index: 117557 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5639. Min Act: -0.0000

Data Index: 365376 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5574. Min Act: -0.0000

Data Index: 765100 (C4 (Web Text))

Max Activating Token Index: 453