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

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

Neuron 3403 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1662. Min Range: -2.1662

Max Act: 2.1662. Min Act: -0.0001

Data Index: 347280 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.8087. Min Act: -0.0000

Data Index: 693996 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.6011. Min Act: -0.0000

Data Index: 1174214 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.5690. Min Act: -0.0000

Data Index: 71817 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.4043. Min Act: -0.0000

Data Index: 992421 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.6452. Min Act: -0.0001

Data Index: 1027314 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.5735. Min Act: -0.0000

Data Index: 548687 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.5916. Min Act: -0.0000

Data Index: 361585 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.5961. Min Act: -0.0000

Data Index: 243378 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.4954. Min Act: -0.0000

Data Index: 976185 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.4793. Min Act: -0.0000

Data Index: 1290488 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.4602. Min Act: -0.0000

Data Index: 925375 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.4117. Min Act: -0.0000

Data Index: 657029 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.5175. Min Act: -0.0000

Data Index: 597489 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1548006 (Python Code)

Max Activating Token Index: 379

Text #15

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.5123. Min Act: -0.0000

Data Index: 160387 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1047198 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.3898. Min Act: -0.0000

Data Index: 351683 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.4151. Min Act: -0.0000

Data Index: 586012 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 2.1662. Min Range: -2.1662

Max Act: 1.4311. Min Act: -0.0000

Data Index: 950253 (C4 (Web Text))

Max Activating Token Index: 271