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

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

Neuron 5945 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1723. Min Range: -1.1723

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1186427 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 1.1723. Min Range: -1.1723

Max Act: 1.1016. Min Act: -0.0000

Data Index: 706777 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9297. Min Act: -0.0000

Data Index: 345198 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1135793 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.8960. Min Act: -0.0000

Data Index: 759355 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.8282. Min Act: -0.0000

Data Index: 556525 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.8022. Min Act: -0.0000

Data Index: 919946 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7784. Min Act: -0.0000

Data Index: 784754 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7737. Min Act: 0.0000

Data Index: 975767 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1072024 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1045425 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7628. Min Act: -0.0000

Data Index: 45704 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1310228 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7535. Min Act: -0.0000

Data Index: 417107 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7533. Min Act: -0.0000

Data Index: 931104 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7238. Min Act: -0.0000

Data Index: 893197 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7651. Min Act: -0.0000

Data Index: 486006 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7620. Min Act: -0.0000

Data Index: 924598 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.6592. Min Act: -0.0000

Data Index: 433259 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1106693 (C4 (Web Text))

Max Activating Token Index: 651