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

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

Neuron 3608 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2872. Min Act: -0.0000

Data Index: 537750 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2548. Min Act: -0.0000

Data Index: 726090 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1034104 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2326. Min Act: -0.0000

Data Index: 786618 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2125. Min Act: -0.0000

Data Index: 557345 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2023. Min Act: -0.0000

Data Index: 253745 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2165. Min Act: -0.0000

Data Index: 890571 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2014. Min Act: -0.0000

Data Index: 393731 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1969. Min Act: -0.0000

Data Index: 747870 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1845. Min Act: -0.0000

Data Index: 721174 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1896. Min Act: -0.0000

Data Index: 734335 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1389068 (Python Code)

Max Activating Token Index: 754

Text #12

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1486059 (Python Code)

Max Activating Token Index: 350

Text #13

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1730. Min Act: -0.0000

Data Index: 339985 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1673. Min Act: -0.0000

Data Index: 250050 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1704. Min Act: -0.0000

Data Index: 332915 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1386611 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1709. Min Act: -0.0000

Data Index: 237624 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1362154 (Python Code)

Max Activating Token Index: 231