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

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

Neuron 2227 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.7636. Min Act: -0.0000

Data Index: 231201 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1085374 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6516. Min Act: -0.0000

Data Index: 447033 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5800. Min Act: -0.0000

Data Index: 1520494 (Python Code)

Max Activating Token Index: 342

Text #4

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1480051 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5267. Min Act: -0.0000

Data Index: 594085 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1476592 (Python Code)

Max Activating Token Index: 946

Text #7

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4993. Min Act: -0.0000

Data Index: 124145 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1432050 (Python Code)

Max Activating Token Index: 745

Text #9

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1360832 (Python Code)

Max Activating Token Index: 697

Text #10

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1296060 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1521644 (Python Code)

Max Activating Token Index: 985

Text #12

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1415850 (Python Code)

Max Activating Token Index: 473

Text #13

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4959. Min Act: -0.0000

Data Index: 136638 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1478195 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1084913 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4888. Min Act: -0.0000

Data Index: 2634 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1431575 (Python Code)

Max Activating Token Index: 556

Text #18

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4742. Min Act: -0.0000

Data Index: 235438 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5201. Min Act: -0.0000

Data Index: 794445 (C4 (Web Text))

Max Activating Token Index: 691