Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5017 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.8600. Min Range: -3.8600

Max Act: 3.8600. Min Act: -0.0001

Data Index: 876776 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 3.8600. Min Range: -3.8600

Max Act: 3.4666. Min Act: -0.0001

Data Index: 215467 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 3.8600. Min Range: -3.8600

Max Act: 3.2112. Min Act: -0.0001

Data Index: 296162 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 3.8600. Min Range: -3.8600

Max Act: 3.1646. Min Act: -0.0001

Data Index: 53400 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 3.8600. Min Range: -3.8600

Max Act: 3.1354. Min Act: -0.0001

Data Index: 561262 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 3.8600. Min Range: -3.8600

Max Act: 2.9632. Min Act: -0.0001

Data Index: 529991 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 3.8600. Min Range: -3.8600

Max Act: 3.0532. Min Act: -0.0001

Data Index: 38975 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 3.8600. Min Range: -3.8600

Max Act: 3.1778. Min Act: -0.0001

Data Index: 603191 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 3.8600. Min Range: -3.8600

Max Act: 3.1217. Min Act: -0.0001

Data Index: 638131 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 3.8600. Min Range: -3.8600

Max Act: 3.1307. Min Act: -0.0001

Data Index: 425454 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 3.8600. Min Range: -3.8600

Max Act: 2.8877. Min Act: -0.0001

Data Index: 885101 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 3.8600. Min Range: -3.8600

Max Act: 2.7619. Min Act: -0.0001

Data Index: 176731 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 3.8600. Min Range: -3.8600

Max Act: 2.8919. Min Act: -0.0001

Data Index: 862443 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 3.8600. Min Range: -3.8600

Max Act: 2.8510. Min Act: -0.0001

Data Index: 207632 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 3.8600. Min Range: -3.8600

Max Act: 2.8231. Min Act: -0.0001

Data Index: 671900 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 3.8600. Min Range: -3.8600

Max Act: 2.7771. Min Act: -0.0001

Data Index: 2614 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 3.8600. Min Range: -3.8600

Max Act: 2.9085. Min Act: -0.0001

Data Index: 1111865 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 3.8600. Min Range: -3.8600

Max Act: 2.5306. Min Act: -0.0001

Data Index: 539203 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 3.8600. Min Range: -3.8600

Max Act: 2.6384. Min Act: -0.0001

Data Index: 703377 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 3.8600. Min Range: -3.8600

Max Act: 2.6645. Min Act: -0.0001

Data Index: 1315302 (C4 (Web Text))

Max Activating Token Index: 919