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

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

Neuron 103 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: 2.6948. Min Range: -2.6948

Max Act: 2.6948. Min Act: -0.0000

Data Index: 174109 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.3432. Min Act: -0.0000

Data Index: 825408 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.0740. Min Act: -0.0000

Data Index: 665365 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.3883. Min Act: -0.0000

Data Index: 547711 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.2896. Min Act: -0.0000

Data Index: 75469 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.1698. Min Act: -0.0000

Data Index: 1075617 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.0481. Min Act: -0.0000

Data Index: 325482 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.4044. Min Act: -0.0000

Data Index: 949150 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.1696. Min Act: -0.0000

Data Index: 1153040 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.3530. Min Act: -0.0000

Data Index: 909690 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 2.6948. Min Range: -2.6948

Max Act: 1.8661. Min Act: -0.0000

Data Index: 484167 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.0092. Min Act: -0.0000

Data Index: 931431 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.0318. Min Act: -0.0000

Data Index: 979041 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.0276. Min Act: -0.0000

Data Index: 1038716 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 2.6948. Min Range: -2.6948

Max Act: 2.0438. Min Act: -0.0000

Data Index: 522617 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 2.6948. Min Range: -2.6948

Max Act: 1.9287. Min Act: -0.0000

Data Index: 1149832 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 2.6948. Min Range: -2.6948

Max Act: 1.8928. Min Act: -0.0000

Data Index: 1197750 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 2.6948. Min Range: -2.6948

Max Act: 1.8413. Min Act: -0.0000

Data Index: 1162627 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 2.6948. Min Range: -2.6948

Max Act: 1.7861. Min Act: -0.0000

Data Index: 214571 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 2.6948. Min Range: -2.6948

Max Act: 1.8016. Min Act: -0.0000

Data Index: 1150834 (C4 (Web Text))

Max Activating Token Index: 59