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

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

Neuron 5911 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0357. Min Range: -1.0357

Max Act: 1.0357. Min Act: -0.0000

Data Index: 6803 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.0357. Min Range: -1.0357

Max Act: 1.0233. Min Act: -0.0000

Data Index: 373753 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 1.0357. Min Range: -1.0357

Max Act: 1.0104. Min Act: -0.0000

Data Index: 56919 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.8890. Min Act: -0.0000

Data Index: 406159 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.9174. Min Act: -0.0000

Data Index: 244672 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.8904. Min Act: -0.0000

Data Index: 760052 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1022896 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.8441. Min Act: -0.0000

Data Index: 284007 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.8330. Min Act: -0.0000

Data Index: 145585 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.7575. Min Act: -0.0000

Data Index: 411746 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.7633. Min Act: -0.0000

Data Index: 330729 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.7594. Min Act: -0.0000

Data Index: 916041 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.7619. Min Act: -0.0000

Data Index: 978437 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.7367. Min Act: -0.0000

Data Index: 75213 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.7641. Min Act: -0.0000

Data Index: 472095 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1350193 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.7646. Min Act: -0.0000

Data Index: 254837 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.7573. Min Act: -0.0000

Data Index: 788137 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.7364. Min Act: -0.0000

Data Index: 500361 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 1.0357. Min Range: -1.0357

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1042179 (C4 (Web Text))

Max Activating Token Index: 676