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

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

Neuron 4237 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.9862. Min Act: -0.0000

Data Index: 901391 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.8166. Min Act: -0.0000

Data Index: 1611344 (Python Code)

Max Activating Token Index: 856

Text #2

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.7510. Min Act: -0.0000

Data Index: 1578006 (Python Code)

Max Activating Token Index: 572

Text #3

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.6003. Min Act: -0.0000

Data Index: 1306699 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.5616. Min Act: -0.0000

Data Index: 1403732 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1508542 (Python Code)

Max Activating Token Index: 707

Text #6

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.5566. Min Act: -0.0000

Data Index: 1439314 (Python Code)

Max Activating Token Index: 457

Text #7

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4931. Min Act: -0.0000

Data Index: 479652 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4810. Min Act: -0.0000

Data Index: 1212903 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4826. Min Act: -0.0000

Data Index: 904046 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4247. Min Act: -0.0000

Data Index: 1612323 (Python Code)

Max Activating Token Index: 1017

Text #11

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4365. Min Act: -0.0000

Data Index: 1642600 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4045. Min Act: -0.0000

Data Index: 1627452 (Python Code)

Max Activating Token Index: 779

Text #13

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4043. Min Act: -0.0000

Data Index: 440617 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4016. Min Act: -0.0000

Data Index: 925471 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4365. Min Act: -0.0000

Data Index: 1374839 (Python Code)

Max Activating Token Index: 877

Text #16

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.3766. Min Act: -0.0000

Data Index: 1630986 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.3767. Min Act: -0.0000

Data Index: 463456 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.3747. Min Act: -0.0000

Data Index: 123087 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.4251. Min Act: -0.0000

Data Index: 1604185 (Python Code)

Max Activating Token Index: 682