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

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

Neuron 6045 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.9944. Min Act: -0.0000

Data Index: 1085034 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.4744. Min Act: -0.0000

Data Index: 514337 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.3585. Min Act: -0.0000

Data Index: 921292 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.4354. Min Act: -0.0000

Data Index: 828328 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.2746. Min Act: -0.0001

Data Index: 1017783 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.3745. Min Act: -0.0000

Data Index: 851703 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.8734. Min Act: -0.0001

Data Index: 13874 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.9521. Min Act: -0.0000

Data Index: 1115052 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.9280. Min Act: -0.0000

Data Index: 1278079 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.8665. Min Act: -0.0000

Data Index: 860801 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6917. Min Act: -0.0000

Data Index: 823673 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.0986. Min Act: -0.0000

Data Index: 138035 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.7365. Min Act: -0.0000

Data Index: 1189437 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.7176. Min Act: -0.0000

Data Index: 610712 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.7624. Min Act: -0.0000

Data Index: 1007747 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6697. Min Act: -0.0000

Data Index: 1121902 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.7250. Min Act: -0.0000

Data Index: 979905 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6335. Min Act: -0.0000

Data Index: 769981 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.7060. Min Act: -0.0000

Data Index: 1094093 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6521. Min Act: -0.0000

Data Index: 455092 (C4 (Web Text))

Max Activating Token Index: 454