Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5115 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1454. Min Act: -0.0001

Data Index: 828762 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1057490 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1297625 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1293. Min Act: -0.0001

Data Index: 510329 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1260. Min Act: -0.0001

Data Index: 784697 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1207. Min Act: -0.0001

Data Index: 180613 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1147. Min Act: -0.0001

Data Index: 334519 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1099. Min Act: -0.0001

Data Index: 12801 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1148. Min Act: -0.0001

Data Index: 729004 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1084. Min Act: -0.0000

Data Index: 823313 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1175. Min Act: -0.0001

Data Index: 687133 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1126. Min Act: -0.0001

Data Index: 760345 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1157. Min Act: -0.0001

Data Index: 334209 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1109. Min Act: -0.0001

Data Index: 846574 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1131. Min Act: -0.0001

Data Index: 141617 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1121. Min Act: -0.0001

Data Index: 421876 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1110. Min Act: -0.0001

Data Index: 102912 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1080. Min Act: -0.0001

Data Index: 918339 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1282233 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1055. Min Act: -0.0001

Data Index: 247574 (C4 (Web Text))

Max Activating Token Index: 906