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

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

Neuron 1340 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.4392. Min Act: -0.0001

Data Index: 527864 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.4812. Min Act: -0.0001

Data Index: 326667 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.4783. Min Act: -0.0000

Data Index: 1656955 (Python Code)

Max Activating Token Index: 647

Text #3

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.4880. Min Act: -0.0000

Data Index: 921556 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1863. Min Act: -0.0001

Data Index: 901793 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.2735. Min Act: -0.0001

Data Index: 765587 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.2265. Min Act: -0.0001

Data Index: 180262 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1640. Min Act: -0.0001

Data Index: 638664 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1631. Min Act: -0.0000

Data Index: 1274759 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.0302. Min Act: -0.0000

Data Index: 703945 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.0719. Min Act: -0.0000

Data Index: 1323711 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.0585. Min Act: -0.0000

Data Index: 415917 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.0201. Min Act: -0.0001

Data Index: 1541781 (Python Code)

Max Activating Token Index: 991

Text #13

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1417. Min Act: -0.0001

Data Index: 174538 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1343229 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.0677. Min Act: -0.0000

Data Index: 909620 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.0306. Min Act: -0.0001

Data Index: 812810 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1226217 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 1.4880. Min Range: -1.4880

Max Act: 0.9961. Min Act: -0.0001

Data Index: 1075816 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.4880. Min Range: -1.4880

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1299748 (C4 (Web Text))

Max Activating Token Index: 610