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

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

Neuron 4412 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: 0.3221. Min Range: -0.3221

Max Act: 0.3221. Min Act: -0.0001

Data Index: 1446546 (Python Code)

Max Activating Token Index: 535

Text #1

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2561. Min Act: -0.0001

Data Index: 1501689 (Python Code)

Max Activating Token Index: 167

Text #2

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2188. Min Act: -0.0001

Data Index: 764653 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2310. Min Act: -0.0001

Data Index: 898319 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1992. Min Act: -0.0001

Data Index: 807152 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1927. Min Act: -0.0000

Data Index: 855058 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1880. Min Act: -0.0001

Data Index: 457938 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1885. Min Act: -0.0001

Data Index: 881225 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2080. Min Act: -0.0001

Data Index: 875135 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1875. Min Act: -0.0000

Data Index: 462178 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1893. Min Act: -0.0001

Data Index: 896503 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1195982 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1238290 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1702. Min Act: -0.0000

Data Index: 116826 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1590. Min Act: -0.0000

Data Index: 993066 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1793. Min Act: -0.0001

Data Index: 506493 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1994. Min Act: -0.0001

Data Index: 1266441 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1700. Min Act: -0.0001

Data Index: 640046 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1432033 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1779. Min Act: -0.0001

Data Index: 95953 (C4 (Web Text))

Max Activating Token Index: 499