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

Dataset: The Pile

Neuron 3713 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.4385. Min Act: -0.0000

Data Index: 242686 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3809. Min Act: -0.0000

Data Index: 17957 (The Pile)

Max Activating Token Index: 979

Text #2

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3158. Min Act: -0.0000

Data Index: 604561 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1662028 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3122. Min Act: -0.0000

Data Index: 1026950 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2941. Min Act: -0.0000

Data Index: 984969 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1130055 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3142. Min Act: -0.0000

Data Index: 773395 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2883. Min Act: -0.0000

Data Index: 60940 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2748. Min Act: -0.0000

Data Index: 608641 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2614. Min Act: -0.0000

Data Index: 498176 (The Pile)

Max Activating Token Index: 202

Text #11

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2663. Min Act: -0.0000

Data Index: 548523 (The Pile)

Max Activating Token Index: 974

Text #12

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1610020 (The Pile)

Max Activating Token Index: 531

Text #13

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2606. Min Act: -0.0000

Data Index: 702744 (The Pile)

Max Activating Token Index: 336

Text #14

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2591. Min Act: -0.0000

Data Index: 857365 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1078034 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2573. Min Act: -0.0000

Data Index: 792168 (The Pile)

Max Activating Token Index: 745

Text #17

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2563. Min Act: -0.0000

Data Index: 522425 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1668010 (The Pile)

Max Activating Token Index: 112

Text #19

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1523476 (The Pile)

Max Activating Token Index: 798