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

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

Neuron 1778 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4539. Min Range: -5.4539

Max Act: 5.4539. Min Act: -0.0001

Data Index: 677960 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.8274. Min Act: -0.0001

Data Index: 938614 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.4435. Min Act: -0.0000

Data Index: 969772 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.7806. Min Act: -0.0000

Data Index: 1268441 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.6119. Min Act: -0.0000

Data Index: 667052 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.6190. Min Act: -0.0001

Data Index: 869151 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.5655. Min Act: -0.0000

Data Index: 365287 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.5438. Min Act: -0.0001

Data Index: 142990 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.8943. Min Act: -0.0000

Data Index: 172291 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.6626. Min Act: -0.0000

Data Index: 155315 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.5032. Min Act: -0.0001

Data Index: 1232826 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.2949. Min Act: -0.0000

Data Index: 545132 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.4481. Min Act: -0.0000

Data Index: 213584 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.4306. Min Act: -0.0001

Data Index: 584167 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.4449. Min Act: -0.0000

Data Index: 656376 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.4217. Min Act: -0.0000

Data Index: 114946 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.3839. Min Act: -0.0000

Data Index: 792320 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.3294. Min Act: -0.0001

Data Index: 377176 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.4785. Min Act: -0.0000

Data Index: 806265 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.4277. Min Act: -0.0000

Data Index: 1144325 (C4 (Web Text))

Max Activating Token Index: 787