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

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

Neuron 1020 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5780. Min Range: -6.5780

Max Act: 6.5780. Min Act: -0.0000

Data Index: 794837 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 6.5780. Min Range: -6.5780

Max Act: 5.6874. Min Act: -0.0000

Data Index: 1325485 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 6.5780. Min Range: -6.5780

Max Act: 5.5931. Min Act: -0.0000

Data Index: 372415 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 6.5780. Min Range: -6.5780

Max Act: 5.7150. Min Act: -0.0000

Data Index: 64352 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 6.5780. Min Range: -6.5780

Max Act: 5.5926. Min Act: -0.0000

Data Index: 115934 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 6.5780. Min Range: -6.5780

Max Act: 5.6985. Min Act: -0.0000

Data Index: 1136787 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 6.5780. Min Range: -6.5780

Max Act: 5.4671. Min Act: -0.0000

Data Index: 181929 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 6.5780. Min Range: -6.5780

Max Act: 5.1483. Min Act: -0.0000

Data Index: 25420 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 6.5780. Min Range: -6.5780

Max Act: 4.5799. Min Act: -0.0000

Data Index: 1303483 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 6.5780. Min Range: -6.5780

Max Act: 5.2923. Min Act: -0.0000

Data Index: 944872 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 6.5780. Min Range: -6.5780

Max Act: 4.8774. Min Act: -0.0000

Data Index: 748313 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 6.5780. Min Range: -6.5780

Max Act: 4.6229. Min Act: -0.0000

Data Index: 202473 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 6.5780. Min Range: -6.5780

Max Act: 5.1330. Min Act: -0.0000

Data Index: 645244 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 6.5780. Min Range: -6.5780

Max Act: 4.5236. Min Act: -0.0000

Data Index: 781817 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 6.5780. Min Range: -6.5780

Max Act: 4.4887. Min Act: -0.0000

Data Index: 292095 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 6.5780. Min Range: -6.5780

Max Act: 4.8540. Min Act: -0.0000

Data Index: 1112868 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 6.5780. Min Range: -6.5780

Max Act: 4.8183. Min Act: -0.0000

Data Index: 801514 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 6.5780. Min Range: -6.5780

Max Act: 4.7911. Min Act: -0.0000

Data Index: 418211 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 6.5780. Min Range: -6.5780

Max Act: 4.3585. Min Act: -0.0000

Data Index: 86539 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 6.5780. Min Range: -6.5780

Max Act: 4.9020. Min Act: -0.0000

Data Index: 1239126 (C4 (Web Text))

Max Activating Token Index: 910