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

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

Neuron 559 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2389. Min Act: -0.0001

Data Index: 706983 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2028. Min Act: -0.0001

Data Index: 1349056 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2137. Min Act: -0.0001

Data Index: 307863 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1337559 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2056. Min Act: -0.0001

Data Index: 611177 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2190. Min Act: -0.0001

Data Index: 1172763 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1244639 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2018. Min Act: -0.0001

Data Index: 1099 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2002. Min Act: -0.0001

Data Index: 77182 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2056. Min Act: -0.0001

Data Index: 578682 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2029. Min Act: -0.0001

Data Index: 258562 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1938. Min Act: -0.0001

Data Index: 183973 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2002. Min Act: -0.0001

Data Index: 722150 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2092. Min Act: -0.0001

Data Index: 11546 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1924. Min Act: -0.0001

Data Index: 369514 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1281431 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1889. Min Act: -0.0001

Data Index: 194085 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2019. Min Act: -0.0001

Data Index: 1099246 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1062706 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1839. Min Act: -0.0001

Data Index: 907236 (C4 (Web Text))

Max Activating Token Index: 665