Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1004 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2940. Min Act: -0.0003

Data Index: 113780 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2912. Min Act: -0.0003

Data Index: 685037 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2500. Min Act: -0.0003

Data Index: 1164936 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2508. Min Act: -0.0003

Data Index: 1144072 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2178. Min Act: -0.0003

Data Index: 1277748 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2151. Min Act: -0.0003

Data Index: 294459 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2286. Min Act: -0.0003

Data Index: 660191 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2054. Min Act: -0.0003

Data Index: 369858 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2037. Min Act: -0.0003

Data Index: 33556 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2038. Min Act: -0.0003

Data Index: 306821 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1996. Min Act: -0.0004

Data Index: 368826 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1976. Min Act: -0.0003

Data Index: 888457 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1980. Min Act: -0.0003

Data Index: 1052577 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1850. Min Act: -0.0003

Data Index: 1184990 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1937. Min Act: -0.0003

Data Index: 537285 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1883. Min Act: -0.0003

Data Index: 1308566 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1916. Min Act: -0.0003

Data Index: 920381 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1793. Min Act: -0.0003

Data Index: 765913 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1836. Min Act: -0.0003

Data Index: 184841 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1866. Min Act: -0.0003

Data Index: 190250 (C4 (Web Text))

Max Activating Token Index: 981