Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3434 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.4066. Min Act: -0.0001

Data Index: 1150365 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.3050. Min Act: -0.0001

Data Index: 473105 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2927. Min Act: -0.0000

Data Index: 272228 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.3604. Min Act: -0.0001

Data Index: 164750 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2815. Min Act: -0.0001

Data Index: 484254 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1985. Min Act: -0.0001

Data Index: 354181 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2482. Min Act: -0.0001

Data Index: 1012402 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2299. Min Act: -0.0001

Data Index: 560762 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1808. Min Act: -0.0001

Data Index: 771050 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2556. Min Act: -0.0001

Data Index: 387875 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2363. Min Act: -0.0001

Data Index: 1295186 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1959. Min Act: -0.0001

Data Index: 668515 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1949. Min Act: -0.0001

Data Index: 180896 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1880. Min Act: -0.0001

Data Index: 1223635 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1841. Min Act: -0.0001

Data Index: 773575 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1164175 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1768. Min Act: -0.0000

Data Index: 644141 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1577. Min Act: -0.0001

Data Index: 359847 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1876. Min Act: -0.0001

Data Index: 919406 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1512. Min Act: -0.0001

Data Index: 636762 (C4 (Web Text))

Max Activating Token Index: 8