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

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

Neuron 775 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: 0.1064. Min Range: -0.1064

Max Act: 0.1064. Min Act: -0.0001

Data Index: 838717 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1169043 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1048. Min Act: -0.0001

Data Index: 336099 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1009. Min Act: -0.0001

Data Index: 691798 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0973. Min Act: -0.0001

Data Index: 509569 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0963. Min Act: -0.0001

Data Index: 400273 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0936. Min Act: -0.0001

Data Index: 542202 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1146948 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0907. Min Act: -0.0001

Data Index: 310104 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0937. Min Act: -0.0001

Data Index: 196524 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0902. Min Act: -0.0001

Data Index: 151899 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0934. Min Act: -0.0001

Data Index: 34012 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0923. Min Act: -0.0001

Data Index: 397992 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1149230 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0957. Min Act: -0.0001

Data Index: 586182 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1106994 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0902. Min Act: -0.0001

Data Index: 680881 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0906. Min Act: -0.0001

Data Index: 25167 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0897. Min Act: -0.0001

Data Index: 896154 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0890. Min Act: -0.0001

Data Index: 67358 (C4 (Web Text))

Max Activating Token Index: 166