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

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

Neuron 3293 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: 1.4648. Min Range: -1.4648

Max Act: 1.4648. Min Act: -0.0000

Data Index: 1521833 (Python Code)

Max Activating Token Index: 228

Text #1

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2971. Min Act: -0.0000

Data Index: 1469548 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1381445 (Python Code)

Max Activating Token Index: 196

Text #3

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.4578. Min Act: -0.0000

Data Index: 1596300 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1500227 (Python Code)

Max Activating Token Index: 230

Text #5

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.3816. Min Act: -0.0000

Data Index: 1624000 (Python Code)

Max Activating Token Index: 746

Text #6

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1625194 (Python Code)

Max Activating Token Index: 771

Text #7

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.3183. Min Act: -0.0000

Data Index: 1638252 (Python Code)

Max Activating Token Index: 440

Text #8

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2395. Min Act: -0.0000

Data Index: 1568589 (Python Code)

Max Activating Token Index: 809

Text #9

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.3163. Min Act: -0.0000

Data Index: 1558493 (Python Code)

Max Activating Token Index: 697

Text #10

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.3162. Min Act: -0.0000

Data Index: 1476944 (Python Code)

Max Activating Token Index: 589

Text #11

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.3406. Min Act: -0.0000

Data Index: 1581024 (Python Code)

Max Activating Token Index: 260

Text #12

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2668. Min Act: -0.0000

Data Index: 1554804 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2285. Min Act: -0.0000

Data Index: 1507372 (Python Code)

Max Activating Token Index: 97

Text #14

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1506194 (Python Code)

Max Activating Token Index: 976

Text #15

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2770. Min Act: -0.0000

Data Index: 1403883 (Python Code)

Max Activating Token Index: 958

Text #16

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1599719 (Python Code)

Max Activating Token Index: 56

Text #17

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1640209 (Python Code)

Max Activating Token Index: 692

Text #18

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2609. Min Act: -0.0000

Data Index: 1404493 (Python Code)

Max Activating Token Index: 146

Text #19

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1495615 (Python Code)

Max Activating Token Index: 837