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

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

Neuron 3194 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: 4.1840. Min Range: -4.1840

Max Act: 4.1840. Min Act: -0.0000

Data Index: 72778 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 4.1840. Min Range: -4.1840

Max Act: 3.7736. Min Act: -0.0000

Data Index: 1147308 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 4.1840. Min Range: -4.1840

Max Act: 3.5667. Min Act: -0.0000

Data Index: 498764 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 4.1840. Min Range: -4.1840

Max Act: 3.6189. Min Act: -0.0000

Data Index: 276577 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 4.1840. Min Range: -4.1840

Max Act: 3.4368. Min Act: -0.0000

Data Index: 832015 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 4.1840. Min Range: -4.1840

Max Act: 3.3785. Min Act: -0.0000

Data Index: 841557 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 4.1840. Min Range: -4.1840

Max Act: 3.2537. Min Act: -0.0000

Data Index: 67719 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 4.1840. Min Range: -4.1840

Max Act: 3.0248. Min Act: -0.0000

Data Index: 548719 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 4.1840. Min Range: -4.1840

Max Act: 3.1239. Min Act: -0.0000

Data Index: 585526 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 4.1840. Min Range: -4.1840

Max Act: 3.0797. Min Act: -0.0000

Data Index: 1130101 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 4.1840. Min Range: -4.1840

Max Act: 2.8011. Min Act: -0.0000

Data Index: 954899 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 4.1840. Min Range: -4.1840

Max Act: 3.0154. Min Act: -0.0000

Data Index: 638012 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 4.1840. Min Range: -4.1840

Max Act: 2.8347. Min Act: -0.0000

Data Index: 351518 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 4.1840. Min Range: -4.1840

Max Act: 2.8199. Min Act: -0.0000

Data Index: 819569 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 4.1840. Min Range: -4.1840

Max Act: 2.8286. Min Act: -0.0000

Data Index: 1320365 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 4.1840. Min Range: -4.1840

Max Act: 2.8887. Min Act: 0.0001

Data Index: 776619 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 4.1840. Min Range: -4.1840

Max Act: 2.8685. Min Act: -0.0000

Data Index: 732672 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 4.1840. Min Range: -4.1840

Max Act: 2.5789. Min Act: -0.0000

Data Index: 406345 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 4.1840. Min Range: -4.1840

Max Act: 2.8429. Min Act: -0.0000

Data Index: 1014345 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 4.1840. Min Range: -4.1840

Max Act: 2.6042. Min Act: -0.0000

Data Index: 1027923 (C4 (Web Text))

Max Activating Token Index: 38