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

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

Neuron 5282 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1101506 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1398. Min Act: -0.0000

Data Index: 958958 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1529395 (Python Code)

Max Activating Token Index: 465

Text #3

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1590678 (Python Code)

Max Activating Token Index: 323

Text #4

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1179. Min Act: -0.0000

Data Index: 897396 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1609581 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1557272 (Python Code)

Max Activating Token Index: 945

Text #7

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1115. Min Act: -0.0000

Data Index: 186034 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1265366 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1631777 (Python Code)

Max Activating Token Index: 539

Text #10

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1372504 (Python Code)

Max Activating Token Index: 522

Text #11

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1427595 (Python Code)

Max Activating Token Index: 879

Text #12

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1460297 (Python Code)

Max Activating Token Index: 728

Text #13

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1376586 (Python Code)

Max Activating Token Index: 730

Text #14

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1104. Min Act: -0.0000

Data Index: 950676 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1395420 (Python Code)

Max Activating Token Index: 828

Text #16

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1062. Min Act: -0.0000

Data Index: 217581 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1039879 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1656654 (Python Code)

Max Activating Token Index: 957

Text #19

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1377520 (Python Code)

Max Activating Token Index: 687