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

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

Neuron 5658 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.3409. Min Act: -0.0001

Data Index: 1076051 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.3101. Min Act: -0.0001

Data Index: 1227444 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2950. Min Act: -0.0001

Data Index: 1299834 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2873. Min Act: -0.0001

Data Index: 619996 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2879. Min Act: -0.0001

Data Index: 1088902 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2853. Min Act: -0.0001

Data Index: 288042 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2674. Min Act: -0.0001

Data Index: 836683 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2095. Min Act: -0.0001

Data Index: 930196 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2276. Min Act: -0.0001

Data Index: 122917 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2072. Min Act: -0.0001

Data Index: 241910 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1141404 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.1942. Min Act: -0.0001

Data Index: 1149251 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.1743. Min Act: -0.0001

Data Index: 753809 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.1895. Min Act: -0.0001

Data Index: 357903 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.1674. Min Act: -0.0001

Data Index: 753063 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.1582. Min Act: -0.0001

Data Index: 653381 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.1741. Min Act: -0.0001

Data Index: 81988 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.1600. Min Act: -0.0001

Data Index: 926950 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.1701. Min Act: -0.0001

Data Index: 462727 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.1686. Min Act: -0.0001

Data Index: 145133 (C4 (Web Text))

Max Activating Token Index: 68