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

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

Neuron 1712 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: 2.2889. Min Range: -2.2889

Max Act: 2.2889. Min Act: 0.0000

Data Index: 521792 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 2.2889. Min Range: -2.2889

Max Act: 2.2574. Min Act: 0.0001

Data Index: 365857 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 2.2889. Min Range: -2.2889

Max Act: 2.2847. Min Act: -0.0000

Data Index: 993374 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 2.2889. Min Range: -2.2889

Max Act: 2.0613. Min Act: 0.0000

Data Index: 1046612 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 2.2889. Min Range: -2.2889

Max Act: 2.0548. Min Act: -0.0000

Data Index: 851476 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 2.2889. Min Range: -2.2889

Max Act: 2.1217. Min Act: -0.0000

Data Index: 1645825 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.9115. Min Act: -0.0000

Data Index: 116422 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.7782. Min Act: 0.0000

Data Index: 295238 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.6479. Min Act: 0.0000

Data Index: 334449 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.7480. Min Act: -0.0000

Data Index: 1333326 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.7134. Min Act: 0.0000

Data Index: 1038037 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.7507. Min Act: 0.0000

Data Index: 470981 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.6947. Min Act: 0.0000

Data Index: 1154643 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.6425. Min Act: 0.0000

Data Index: 1071366 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.6399. Min Act: -0.0000

Data Index: 145860 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.7233. Min Act: -0.0000

Data Index: 1645373 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.7087. Min Act: 0.0001

Data Index: 611758 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.5190. Min Act: 0.0000

Data Index: 608 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.4838. Min Act: 0.0000

Data Index: 501014 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 2.2889. Min Range: -2.2889

Max Act: 1.5589. Min Act: 0.0000

Data Index: 1189510 (C4 (Web Text))

Max Activating Token Index: 282