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

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

Neuron 1597 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: 4.6672. Min Range: -4.6672

Max Act: 4.6672. Min Act: -0.0000

Data Index: 1153671 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 4.6672. Min Range: -4.6672

Max Act: 4.4827. Min Act: -0.0000

Data Index: 117652 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 4.6672. Min Range: -4.6672

Max Act: 4.5031. Min Act: -0.0000

Data Index: 408121 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 4.6672. Min Range: -4.6672

Max Act: 4.5109. Min Act: -0.0000

Data Index: 147230 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 4.6672. Min Range: -4.6672

Max Act: 4.4007. Min Act: -0.0000

Data Index: 194710 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 4.6672. Min Range: -4.6672

Max Act: 4.3412. Min Act: -0.0000

Data Index: 704918 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 4.6672. Min Range: -4.6672

Max Act: 4.3271. Min Act: -0.0000

Data Index: 265757 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 4.6672. Min Range: -4.6672

Max Act: 4.2563. Min Act: -0.0000

Data Index: 496714 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 4.6672. Min Range: -4.6672

Max Act: 4.2431. Min Act: -0.0000

Data Index: 166245 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 4.6672. Min Range: -4.6672

Max Act: 3.9877. Min Act: -0.0000

Data Index: 1307333 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 4.6672. Min Range: -4.6672

Max Act: 4.1415. Min Act: -0.0000

Data Index: 26098 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 4.6672. Min Range: -4.6672

Max Act: 4.1542. Min Act: -0.0000

Data Index: 341140 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 4.6672. Min Range: -4.6672

Max Act: 4.1902. Min Act: -0.0000

Data Index: 130 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 4.6672. Min Range: -4.6672

Max Act: 3.9779. Min Act: -0.0000

Data Index: 980346 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 4.6672. Min Range: -4.6672

Max Act: 3.9715. Min Act: -0.0000

Data Index: 1279065 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 4.6672. Min Range: -4.6672

Max Act: 3.9136. Min Act: -0.0000

Data Index: 507070 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 4.6672. Min Range: -4.6672

Max Act: 3.7921. Min Act: -0.0000

Data Index: 736500 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 4.6672. Min Range: -4.6672

Max Act: 3.6020. Min Act: -0.0000

Data Index: 566675 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 4.6672. Min Range: -4.6672

Max Act: 3.7106. Min Act: -0.0000

Data Index: 1100537 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 4.6672. Min Range: -4.6672

Max Act: 3.5393. Min Act: -0.0000

Data Index: 863472 (C4 (Web Text))

Max Activating Token Index: 812