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

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

Neuron 3160 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.3016. Min Act: -0.0000

Data Index: 802452 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.2301. Min Act: -0.0000

Data Index: 674635 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1354661 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.2241. Min Act: -0.0001

Data Index: 338713 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.2073. Min Act: -0.0000

Data Index: 216657 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1906. Min Act: -0.0001

Data Index: 848576 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1192191 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1862. Min Act: -0.0001

Data Index: 1140517 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1795. Min Act: -0.0001

Data Index: 865246 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1798. Min Act: -0.0000

Data Index: 521066 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1786. Min Act: -0.0001

Data Index: 23778 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1778. Min Act: -0.0001

Data Index: 920991 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1837. Min Act: -0.0001

Data Index: 42730 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1691. Min Act: -0.0001

Data Index: 859559 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1692. Min Act: -0.0001

Data Index: 151705 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1805. Min Act: -0.0001

Data Index: 816109 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1746. Min Act: -0.0001

Data Index: 472204 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1679. Min Act: -0.0001

Data Index: 852055 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1749. Min Act: -0.0001

Data Index: 266894 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.3016. Min Range: -0.3016

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1052610 (C4 (Web Text))

Max Activating Token Index: 192