Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 139 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.9514. Min Act: -0.0001

Data Index: 1385216 (Python Code)

Max Activating Token Index: 68

Text #1

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.9253. Min Act: -0.0001

Data Index: 1379991 (Python Code)

Max Activating Token Index: 148

Text #2

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.9025. Min Act: -0.0001

Data Index: 1649903 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8223. Min Act: -0.0001

Data Index: 1644132 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8367. Min Act: -0.0001

Data Index: 1580285 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.9680. Min Act: -0.0001

Data Index: 1441579 (Python Code)

Max Activating Token Index: 297

Text #6

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.9432. Min Act: -0.0001

Data Index: 1553638 (Python Code)

Max Activating Token Index: 255

Text #7

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7576. Min Act: -0.0001

Data Index: 1431552 (Python Code)

Max Activating Token Index: 667

Text #8

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8489. Min Act: -0.0001

Data Index: 1576818 (Python Code)

Max Activating Token Index: 177

Text #9

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8653. Min Act: -0.0001

Data Index: 1610880 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1572542 (Python Code)

Max Activating Token Index: 216

Text #11

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8175. Min Act: -0.0001

Data Index: 1393832 (Python Code)

Max Activating Token Index: 956

Text #12

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8620. Min Act: -0.0001

Data Index: 1569189 (Python Code)

Max Activating Token Index: 990

Text #13

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8415. Min Act: -0.0001

Data Index: 1405648 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8122. Min Act: -0.0001

Data Index: 1379994 (Python Code)

Max Activating Token Index: 17

Text #15

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8354. Min Act: -0.0001

Data Index: 1386994 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7993. Min Act: -0.0001

Data Index: 1626818 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7925. Min Act: -0.0001

Data Index: 1584853 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8128. Min Act: -0.0001

Data Index: 1632604 (Python Code)

Max Activating Token Index: 134

Text #19

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8126. Min Act: -0.0001

Data Index: 1380167 (Python Code)

Max Activating Token Index: 8