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

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

Neuron 4957 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1865. Min Act: -0.0001

Data Index: 851619 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9749. Min Act: -0.0001

Data Index: 258063 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0281. Min Act: -0.0001

Data Index: 1291911 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8651. Min Act: -0.0001

Data Index: 707831 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8231. Min Act: -0.0001

Data Index: 455939 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8746. Min Act: -0.0001

Data Index: 1101373 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.7668. Min Act: -0.0001

Data Index: 493882 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8489. Min Act: -0.0001

Data Index: 350486 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8226. Min Act: -0.0001

Data Index: 726698 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.7188. Min Act: -0.0001

Data Index: 958872 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.6696. Min Act: -0.0001

Data Index: 473083 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.7540. Min Act: -0.0001

Data Index: 307024 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.6765. Min Act: -0.0001

Data Index: 282803 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.6814. Min Act: -0.0001

Data Index: 1036899 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.7603. Min Act: -0.0001

Data Index: 461276 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.6733. Min Act: -0.0001

Data Index: 1131222 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.7481. Min Act: -0.0001

Data Index: 1055784 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.6870. Min Act: -0.0001

Data Index: 885578 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.7285. Min Act: -0.0001

Data Index: 1042265 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.6562. Min Act: -0.0001

Data Index: 924410 (C4 (Web Text))

Max Activating Token Index: 842