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

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

Neuron 1497 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: 3.5849. Min Range: -3.5849

Max Act: 3.4818. Min Act: -0.0000

Data Index: 1016349 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 3.5849. Min Range: -3.5849

Max Act: 3.5849. Min Act: -0.0000

Data Index: 1166068 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.9991. Min Act: -0.0000

Data Index: 605869 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.5849. Min Range: -3.5849

Max Act: 3.2248. Min Act: -0.0000

Data Index: 571918 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 3.5849. Min Range: -3.5849

Max Act: 3.0570. Min Act: -0.0000

Data Index: 1170744 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.9046. Min Act: -0.0000

Data Index: 1046517 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 3.5849. Min Range: -3.5849

Max Act: 3.0685. Min Act: -0.0000

Data Index: 1334145 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.9198. Min Act: -0.0000

Data Index: 622147 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.6236. Min Act: -0.0000

Data Index: 1527855 (Python Code)

Max Activating Token Index: 799

Text #9

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.7183. Min Act: -0.0000

Data Index: 1275503 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.7791. Min Act: -0.0000

Data Index: 382937 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.6428. Min Act: -0.0000

Data Index: 698616 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.8729. Min Act: -0.0000

Data Index: 733270 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.5964. Min Act: -0.0000

Data Index: 663692 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.6003. Min Act: -0.0000

Data Index: 157459 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.8404. Min Act: -0.0000

Data Index: 431865 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.6800. Min Act: -0.0000

Data Index: 506708 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.5622. Min Act: -0.0000

Data Index: 178132 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.8243. Min Act: -0.0000

Data Index: 467170 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 3.5849. Min Range: -3.5849

Max Act: 2.6997. Min Act: -0.0000

Data Index: 690090 (C4 (Web Text))

Max Activating Token Index: 733