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

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

Neuron 2527 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2376. Min Act: -0.0000

Data Index: 997223 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1341799 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2461. Min Act: -0.0000

Data Index: 920916 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1298252 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2085. Min Act: -0.0000

Data Index: 560088 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1067020 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1987. Min Act: -0.0000

Data Index: 880821 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1967. Min Act: -0.0000

Data Index: 724656 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1988. Min Act: -0.0000

Data Index: 43574 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1827. Min Act: -0.0000

Data Index: 276015 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1348971 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1730. Min Act: -0.0000

Data Index: 523117 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1864. Min Act: -0.0000

Data Index: 684059 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1180478 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1844. Min Act: -0.0000

Data Index: 969464 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1579. Min Act: -0.0000

Data Index: 700896 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1646. Min Act: -0.0000

Data Index: 145677 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1352621 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1683. Min Act: -0.0000

Data Index: 889821 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1663. Min Act: -0.0000

Data Index: 439012 (C4 (Web Text))

Max Activating Token Index: 65