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

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

Neuron 4946 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1905. Min Act: -0.0000

Data Index: 407836 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1584. Min Act: -0.0000

Data Index: 359421 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1290535 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1055195 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1334. Min Act: -0.0000

Data Index: 261609 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1228. Min Act: -0.0000

Data Index: 985843 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1022300 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1472096 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1214. Min Act: -0.0000

Data Index: 550483 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1142. Min Act: -0.0000

Data Index: 378985 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1130887 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1217. Min Act: -0.0000

Data Index: 601572 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1315784 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1407490 (Python Code)

Max Activating Token Index: 451

Text #14

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1135. Min Act: -0.0000

Data Index: 988859 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1129. Min Act: -0.0000

Data Index: 656517 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1093. Min Act: -0.0000

Data Index: 993937 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1044. Min Act: -0.0000

Data Index: 300559 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1294463 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1136608 (C4 (Web Text))

Max Activating Token Index: 1012