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

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

Neuron 2237 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2316. Min Act: -0.0000

Data Index: 94621 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2365. Min Act: -0.0000

Data Index: 569447 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1304881 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2311. Min Act: 0.0000

Data Index: 1046209 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2048. Min Act: -0.0000

Data Index: 590708 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1900. Min Act: -0.0000

Data Index: 622316 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1849. Min Act: -0.0000

Data Index: 436699 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1310889 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1827. Min Act: -0.0000

Data Index: 987155 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1872. Min Act: -0.0000

Data Index: 121707 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1088517 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1778. Min Act: 0.0000

Data Index: 358554 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1704. Min Act: -0.0000

Data Index: 405755 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1776. Min Act: 0.0000

Data Index: 505245 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1760. Min Act: -0.0000

Data Index: 517881 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1740. Min Act: -0.0000

Data Index: 487956 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1700. Min Act: -0.0000

Data Index: 957937 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1593. Min Act: -0.0000

Data Index: 910313 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1647. Min Act: -0.0000

Data Index: 827658 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1579. Min Act: -0.0000

Data Index: 390161 (C4 (Web Text))

Max Activating Token Index: 311