Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1319 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1886. Min Act: -0.0003

Data Index: 468041 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1922. Min Act: -0.0003

Data Index: 463298 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1942. Min Act: -0.0004

Data Index: 335536 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1901. Min Act: -0.0003

Data Index: 444945 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1891. Min Act: -0.0002

Data Index: 870515 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1868. Min Act: -0.0003

Data Index: 1358907 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1825. Min Act: -0.0003

Data Index: 435161 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1749. Min Act: -0.0003

Data Index: 572211 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1842. Min Act: -0.0002

Data Index: 367185 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1787. Min Act: -0.0003

Data Index: 1007938 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1776. Min Act: -0.0003

Data Index: 1285830 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1658. Min Act: -0.0003

Data Index: 1198203 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1751. Min Act: -0.0003

Data Index: 524962 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1797. Min Act: -0.0003

Data Index: 1294533 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1739. Min Act: -0.0003

Data Index: 693697 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1726. Min Act: -0.0003

Data Index: 368114 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1727. Min Act: -0.0003

Data Index: 528587 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1731. Min Act: -0.0003

Data Index: 1352455 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1728. Min Act: -0.0003

Data Index: 91120 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1722. Min Act: -0.0002

Data Index: 405796 (C4 (Web Text))

Max Activating Token Index: 679