Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2837 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1061318 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2240. Min Act: -0.0000

Data Index: 685220 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1502816 (Python Code)

Max Activating Token Index: 986

Text #3

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1618. Min Act: -0.0000

Data Index: 296788 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2125. Min Act: -0.0000

Data Index: 75828 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2104. Min Act: -0.0000

Data Index: 517572 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2157. Min Act: -0.0000

Data Index: 492263 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1966. Min Act: -0.0000

Data Index: 494216 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2168. Min Act: -0.0000

Data Index: 304672 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1858. Min Act: -0.0000

Data Index: 456776 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1032576 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1925. Min Act: -0.0000

Data Index: 814460 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1759. Min Act: -0.0000

Data Index: 109227 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1828. Min Act: -0.0000

Data Index: 786414 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1432996 (Python Code)

Max Activating Token Index: 851

Text #15

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1817. Min Act: -0.0000

Data Index: 752888 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1334081 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1846. Min Act: -0.0000

Data Index: 205327 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1013513 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1734. Min Act: -0.0000

Data Index: 966323 (C4 (Web Text))

Max Activating Token Index: 110