Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 198 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1141. Min Act: -0.0001

Data Index: 782389 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1220086 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1477341 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0971. Min Act: -0.0001

Data Index: 751806 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0972. Min Act: -0.0001

Data Index: 378446 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0919. Min Act: -0.0001

Data Index: 752523 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1247998 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1322557 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1304711 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0902. Min Act: -0.0001

Data Index: 494988 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0942. Min Act: -0.0001

Data Index: 311020 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0966. Min Act: -0.0001

Data Index: 891202 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1055585 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1060239 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0957. Min Act: -0.0001

Data Index: 412386 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0955. Min Act: -0.0001

Data Index: 91706 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1164104 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1318004 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1213511 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0932. Min Act: -0.0001

Data Index: 146390 (C4 (Web Text))

Max Activating Token Index: 181