Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1460 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2917. Min Range: -3.2917

Max Act: 3.2917. Min Act: -0.0001

Data Index: 183556 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 3.2917. Min Range: -3.2917

Max Act: 3.0639. Min Act: -0.0001

Data Index: 929617 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 3.2917. Min Range: -3.2917

Max Act: 3.0624. Min Act: -0.0000

Data Index: 1069371 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 3.2917. Min Range: -3.2917

Max Act: 3.0105. Min Act: -0.0001

Data Index: 119829 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.7870. Min Act: -0.0000

Data Index: 276082 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.8408. Min Act: -0.0001

Data Index: 1150200 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.7842. Min Act: -0.0000

Data Index: 489078 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.4624. Min Act: -0.0001

Data Index: 1358584 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.7031. Min Act: -0.0001

Data Index: 159903 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.8439. Min Act: -0.0001

Data Index: 197119 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.6776. Min Act: -0.0000

Data Index: 9718 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.6578. Min Act: -0.0001

Data Index: 603071 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.5155. Min Act: -0.0001

Data Index: 641464 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.5556. Min Act: -0.0001

Data Index: 17975 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.7020. Min Act: -0.0000

Data Index: 612094 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.5360. Min Act: -0.0001

Data Index: 1124007 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.6528. Min Act: -0.0001

Data Index: 1187960 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.6295. Min Act: -0.0001

Data Index: 1144635 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.3334. Min Act: -0.0001

Data Index: 836861 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 3.2917. Min Range: -3.2917

Max Act: 2.4417. Min Act: -0.0001

Data Index: 132722 (C4 (Web Text))

Max Activating Token Index: 345