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

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

Neuron 2210 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.8900. Min Act: -0.0001

Data Index: 681055 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.7990. Min Act: -0.0001

Data Index: 1240310 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 3.0315. Min Range: -3.0315

Max Act: 3.0315. Min Act: -0.0001

Data Index: 1019122 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.5664. Min Act: -0.0001

Data Index: 1081832 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.9097. Min Act: -0.0001

Data Index: 640059 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.8400. Min Act: -0.0002

Data Index: 737439 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.5437. Min Act: -0.0001

Data Index: 555219 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.5072. Min Act: -0.0002

Data Index: 87618 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.7604. Min Act: -0.0001

Data Index: 1265440 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.3810. Min Act: -0.0001

Data Index: 514312 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.6187. Min Act: -0.0001

Data Index: 581560 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.2441. Min Act: -0.0001

Data Index: 1314160 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.1663. Min Act: -0.0002

Data Index: 242828 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.3726. Min Act: -0.0002

Data Index: 83494 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.0096. Min Act: -0.0002

Data Index: 1154529 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.5613. Min Act: -0.0002

Data Index: 1352306 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.2836. Min Act: -0.0002

Data Index: 1135397 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.1066. Min Act: -0.0002

Data Index: 820219 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.3716. Min Act: -0.0002

Data Index: 1146076 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.2284. Min Act: -0.0002

Data Index: 758788 (C4 (Web Text))

Max Activating Token Index: 725