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

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

Neuron 275 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8136. Min Range: -2.8136

Max Act: 2.7545. Min Act: -0.0000

Data Index: 12754 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 2.8136. Min Range: -2.8136

Max Act: 2.7097. Min Act: -0.0000

Data Index: 109451 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 2.8136. Min Range: -2.8136

Max Act: 2.8136. Min Act: -0.0000

Data Index: 583386 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 2.8136. Min Range: -2.8136

Max Act: 2.6031. Min Act: -0.0000

Data Index: 480286 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 2.8136. Min Range: -2.8136

Max Act: 2.4720. Min Act: -0.0000

Data Index: 430686 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 2.8136. Min Range: -2.8136

Max Act: 2.4111. Min Act: -0.0000

Data Index: 862213 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 2.8136. Min Range: -2.8136

Max Act: 2.2080. Min Act: -0.0000

Data Index: 849486 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 2.8136. Min Range: -2.8136

Max Act: 2.0468. Min Act: -0.0000

Data Index: 1213792 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 2.8136. Min Range: -2.8136

Max Act: 2.2435. Min Act: -0.0000

Data Index: 71269 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 2.8136. Min Range: -2.8136

Max Act: 2.1074. Min Act: -0.0000

Data Index: 384535 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 2.8136. Min Range: -2.8136

Max Act: 2.1922. Min Act: -0.0000

Data Index: 268763 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 2.8136. Min Range: -2.8136

Max Act: 1.9848. Min Act: -0.0000

Data Index: 638883 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 2.8136. Min Range: -2.8136

Max Act: 1.9439. Min Act: -0.0000

Data Index: 254541 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 2.8136. Min Range: -2.8136

Max Act: 1.9542. Min Act: -0.0000

Data Index: 913364 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 2.8136. Min Range: -2.8136

Max Act: 1.9269. Min Act: -0.0000

Data Index: 484532 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 2.8136. Min Range: -2.8136

Max Act: 1.8275. Min Act: -0.0000

Data Index: 330384 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 2.8136. Min Range: -2.8136

Max Act: 1.9134. Min Act: -0.0000

Data Index: 399551 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 2.8136. Min Range: -2.8136

Max Act: 1.7886. Min Act: -0.0000

Data Index: 995443 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 2.8136. Min Range: -2.8136

Max Act: 1.9715. Min Act: -0.0000

Data Index: 1359364 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 2.8136. Min Range: -2.8136

Max Act: 1.8816. Min Act: -0.0000

Data Index: 765724 (C4 (Web Text))

Max Activating Token Index: 313