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

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

Neuron 2362 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: 2.5624. Min Range: -2.5624

Max Act: 2.5624. Min Act: -0.0000

Data Index: 643965 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 2.5624. Min Range: -2.5624

Max Act: 2.0022. Min Act: -0.0000

Data Index: 446463 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 2.5624. Min Range: -2.5624

Max Act: 2.0097. Min Act: -0.0000

Data Index: 761516 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.7984. Min Act: -0.0000

Data Index: 1096817 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.3973. Min Act: -0.0001

Data Index: 553662 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.7844. Min Act: -0.0001

Data Index: 784018 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.6777. Min Act: -0.0000

Data Index: 1475133 (Python Code)

Max Activating Token Index: 398

Text #7

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.8328. Min Act: -0.0000

Data Index: 110650 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.6231. Min Act: -0.0000

Data Index: 975770 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.6989. Min Act: -0.0000

Data Index: 957030 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.6843. Min Act: -0.0000

Data Index: 1562052 (Python Code)

Max Activating Token Index: 453

Text #11

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.6742. Min Act: -0.0000

Data Index: 1566085 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.5949. Min Act: -0.0000

Data Index: 1257974 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.6039. Min Act: -0.0000

Data Index: 961878 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.7453. Min Act: -0.0001

Data Index: 330607 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.6584. Min Act: -0.0001

Data Index: 865681 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.5461. Min Act: -0.0001

Data Index: 1209849 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.6105. Min Act: -0.0001

Data Index: 302484 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1011758 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 2.5624. Min Range: -2.5624

Max Act: 1.5269. Min Act: -0.0000

Data Index: 522904 (C4 (Web Text))

Max Activating Token Index: 639