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

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

Neuron 4432 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2764. Min Act: -0.0000

Data Index: 269251 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2326. Min Act: -0.0000

Data Index: 116789 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1206937 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2110. Min Act: -0.0000

Data Index: 295750 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2115. Min Act: -0.0000

Data Index: 56794 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1991. Min Act: -0.0000

Data Index: 425382 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2027. Min Act: -0.0000

Data Index: 58556 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1726. Min Act: -0.0000

Data Index: 416535 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1871. Min Act: -0.0000

Data Index: 657582 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1934. Min Act: -0.0000

Data Index: 772704 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1825. Min Act: -0.0000

Data Index: 422285 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1763. Min Act: -0.0000

Data Index: 288953 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1154602 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1849. Min Act: -0.0000

Data Index: 629508 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1171640 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1720. Min Act: -0.0000

Data Index: 935283 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1704. Min Act: -0.0000

Data Index: 160453 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1049796 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1744. Min Act: -0.0000

Data Index: 747773 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1572. Min Act: -0.0000

Data Index: 557565 (C4 (Web Text))

Max Activating Token Index: 148