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

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

Neuron 3831 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: 2.7837. Min Range: -2.7837

Max Act: 2.7653. Min Act: -0.0000

Data Index: 681222 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.7112. Min Act: -0.0000

Data Index: 331186 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.7837. Min Act: -0.0000

Data Index: 333265 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.5280. Min Act: -0.0000

Data Index: 475918 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.6517. Min Act: -0.0000

Data Index: 1237449 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.5920. Min Act: -0.0000

Data Index: 1300793 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.6622. Min Act: -0.0000

Data Index: 30943 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.3183. Min Act: -0.0000

Data Index: 1279012 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.2242. Min Act: -0.0000

Data Index: 6013 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 2.7837. Min Range: -2.7837

Max Act: 1.9561. Min Act: -0.0000

Data Index: 290808 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.4919. Min Act: -0.0000

Data Index: 1055825 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.1290. Min Act: -0.0000

Data Index: 334533 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.0120. Min Act: -0.0000

Data Index: 1325572 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.0947. Min Act: -0.0000

Data Index: 393239 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.4303. Min Act: -0.0000

Data Index: 795143 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.0848. Min Act: -0.0000

Data Index: 819502 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.1772. Min Act: -0.0000

Data Index: 423711 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.0703. Min Act: -0.0000

Data Index: 1317519 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.2674. Min Act: -0.0000

Data Index: 488871 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 2.7837. Min Range: -2.7837

Max Act: 2.2850. Min Act: -0.0000

Data Index: 462114 (C4 (Web Text))

Max Activating Token Index: 1022