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

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

Neuron 834 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: 2.1136. Min Range: -2.1136

Max Act: 2.1136. Min Act: -0.0000

Data Index: 3562 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.9301. Min Act: -0.0000

Data Index: 481729 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 2.1136. Min Range: -2.1136

Max Act: 2.0119. Min Act: -0.0000

Data Index: 80874 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 2.1136. Min Range: -2.1136

Max Act: 2.0137. Min Act: -0.0000

Data Index: 648837 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.9526. Min Act: -0.0000

Data Index: 966633 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.8266. Min Act: -0.0000

Data Index: 615882 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.8047. Min Act: -0.0000

Data Index: 1149090 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.8912. Min Act: -0.0000

Data Index: 427957 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.9928. Min Act: -0.0000

Data Index: 851798 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.7864. Min Act: -0.0000

Data Index: 948608 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.8460. Min Act: -0.0001

Data Index: 46968 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.8312. Min Act: -0.0000

Data Index: 1071286 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.8182. Min Act: -0.0000

Data Index: 150863 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.8102. Min Act: -0.0001

Data Index: 402083 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.7040. Min Act: -0.0000

Data Index: 428871 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.6811. Min Act: -0.0000

Data Index: 83458 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.7972. Min Act: -0.0000

Data Index: 63473 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.7873. Min Act: -0.0000

Data Index: 1343874 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.8005. Min Act: -0.0000

Data Index: 609501 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 2.1136. Min Range: -2.1136

Max Act: 1.6723. Min Act: -0.0000

Data Index: 93434 (C4 (Web Text))

Max Activating Token Index: 839