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

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

Neuron 5674 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4775. Min Range: -2.4775

Max Act: 2.4775. Min Act: -0.0000

Data Index: 1548318 (Python Code)

Max Activating Token Index: 152

Text #1

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.9912. Min Act: -0.0000

Data Index: 1611545 (Python Code)

Max Activating Token Index: 435

Text #2

Max Range: 2.4775. Min Range: -2.4775

Max Act: 2.0735. Min Act: -0.0000

Data Index: 769484 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 2.4775. Min Range: -2.4775

Max Act: 2.0639. Min Act: -0.0000

Data Index: 785198 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 2.4775. Min Range: -2.4775

Max Act: 2.1020. Min Act: -0.0000

Data Index: 1385020 (Python Code)

Max Activating Token Index: 509

Text #5

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.8497. Min Act: -0.0000

Data Index: 1094174 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.9556. Min Act: -0.0000

Data Index: 162037 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.9427. Min Act: -0.0000

Data Index: 1633617 (Python Code)

Max Activating Token Index: 601

Text #8

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.8360. Min Act: -0.0000

Data Index: 360614 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.8797. Min Act: -0.0000

Data Index: 189786 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.7614. Min Act: -0.0000

Data Index: 1483379 (Python Code)

Max Activating Token Index: 318

Text #11

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.7892. Min Act: -0.0000

Data Index: 311206 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.7032. Min Act: -0.0000

Data Index: 815048 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.6649. Min Act: -0.0000

Data Index: 763496 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.6072. Min Act: -0.0000

Data Index: 1556259 (Python Code)

Max Activating Token Index: 771

Text #15

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.6568. Min Act: -0.0000

Data Index: 894132 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.6489. Min Act: -0.0000

Data Index: 896630 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.7245. Min Act: -0.0000

Data Index: 1101978 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.6223. Min Act: -0.0000

Data Index: 884239 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.6528. Min Act: -0.0000

Data Index: 751883 (C4 (Web Text))

Max Activating Token Index: 317