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

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

Neuron 658 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1008. Min Range: -1.1008

Max Act: 1.1008. Min Act: -0.0000

Data Index: 1245516 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9834. Min Act: -0.0000

Data Index: 613664 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 1.1008. Min Range: -1.1008

Max Act: 1.0024. Min Act: -0.0000

Data Index: 96891 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9587. Min Act: -0.0000

Data Index: 423568 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9771. Min Act: -0.0000

Data Index: 318391 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9698. Min Act: -0.0000

Data Index: 589080 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9422. Min Act: -0.0000

Data Index: 768359 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9607. Min Act: -0.0000

Data Index: 736013 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.8607. Min Act: -0.0000

Data Index: 770853 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9147. Min Act: -0.0000

Data Index: 858594 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.8829. Min Act: -0.0000

Data Index: 432950 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.8737. Min Act: -0.0000

Data Index: 23349 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9595. Min Act: -0.0000

Data Index: 319051 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9177. Min Act: -0.0000

Data Index: 797641 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9122. Min Act: -0.0000

Data Index: 738464 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1019471 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9460. Min Act: -0.0000

Data Index: 153466 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1155146 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1021888 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.8859. Min Act: -0.0000

Data Index: 804140 (C4 (Web Text))

Max Activating Token Index: 742