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

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

Neuron 2029 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1307. Min Act: -0.0001

Data Index: 872337 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1075. Min Act: -0.0001

Data Index: 157447 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1083. Min Act: -0.0001

Data Index: 216986 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1039. Min Act: -0.0001

Data Index: 904831 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1239. Min Act: -0.0001

Data Index: 51378 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1062. Min Act: -0.0001

Data Index: 333567 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1116. Min Act: -0.0001

Data Index: 377930 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0963. Min Act: -0.0001

Data Index: 657135 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1058. Min Act: -0.0001

Data Index: 777452 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1076. Min Act: -0.0001

Data Index: 176722 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1324992 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0977. Min Act: -0.0001

Data Index: 384914 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1327936 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1082217 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1140599 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1261454 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1342549 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0956. Min Act: -0.0001

Data Index: 811507 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0934. Min Act: -0.0001

Data Index: 829031 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0935. Min Act: -0.0001

Data Index: 631787 (C4 (Web Text))

Max Activating Token Index: 195