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

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

Neuron 3658 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1328761 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1364. Min Act: -0.0000

Data Index: 809526 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1278. Min Act: -0.0000

Data Index: 770422 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1300. Min Act: -0.0000

Data Index: 33546 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1224. Min Act: 0.0000

Data Index: 119460 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1189. Min Act: -0.0000

Data Index: 693110 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1111. Min Act: -0.0000

Data Index: 913959 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1147. Min Act: -0.0000

Data Index: 568195 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1209. Min Act: 0.0001

Data Index: 87615 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1328745 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1002374 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1349749 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1110. Min Act: 0.0000

Data Index: 496887 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1103. Min Act: -0.0000

Data Index: 265833 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1099. Min Act: -0.0000

Data Index: 188953 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1137. Min Act: -0.0000

Data Index: 72956 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1171. Min Act: -0.0000

Data Index: 607307 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1321694 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1129. Min Act: -0.0000

Data Index: 356481 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1076. Min Act: -0.0000

Data Index: 53981 (C4 (Web Text))

Max Activating Token Index: 230