Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 55 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4694. Min Act: -0.0001

Data Index: 406576 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4600. Min Act: -0.0001

Data Index: 1260852 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4223. Min Act: -0.0001

Data Index: 908845 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.3965. Min Act: -0.0001

Data Index: 13740 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4229. Min Act: -0.0001

Data Index: 1347504 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.3747. Min Act: -0.0001

Data Index: 1069438 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.3575. Min Act: -0.0001

Data Index: 876799 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.3818. Min Act: -0.0001

Data Index: 136067 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.3115. Min Act: -0.0001

Data Index: 666882 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.3058. Min Act: -0.0001

Data Index: 929830 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.3067. Min Act: -0.0001

Data Index: 943930 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.3082. Min Act: -0.0001

Data Index: 551644 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.2729. Min Act: -0.0001

Data Index: 680320 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.2913. Min Act: -0.0001

Data Index: 1230780 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1341179 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.2589. Min Act: -0.0001

Data Index: 819474 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.2725. Min Act: -0.0001

Data Index: 546851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.2834. Min Act: -0.0001

Data Index: 178467 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.2194. Min Act: -0.0001

Data Index: 1260393 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.2323. Min Act: -0.0001

Data Index: 155372 (C4 (Web Text))

Max Activating Token Index: 616