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

Dataset: The Pile

Neuron 3689 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.3377. Min Act: -0.0000

Data Index: 1777015 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1887419 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.4203. Min Act: -0.0000

Data Index: 1650445 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.4592. Min Act: -0.0000

Data Index: 1601440 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.3475. Min Act: -0.0000

Data Index: 484291 (The Pile)

Max Activating Token Index: 409

Text #5

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.3526. Min Act: -0.0000

Data Index: 502224 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2971. Min Act: -0.0000

Data Index: 838773 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.3571. Min Act: -0.0000

Data Index: 533181 (The Pile)

Max Activating Token Index: 282

Text #8

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.3610. Min Act: -0.0000

Data Index: 1128929 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2195. Min Act: -0.0000

Data Index: 1249296 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1317385 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2427. Min Act: -0.0000

Data Index: 1230278 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1089615 (The Pile)

Max Activating Token Index: 873

Text #13

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.3551. Min Act: -0.0000

Data Index: 1372547 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.3855. Min Act: -0.0000

Data Index: 1990139 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2779. Min Act: -0.0000

Data Index: 222524 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1535360 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.3032. Min Act: -0.0000

Data Index: 64032 (The Pile)

Max Activating Token Index: 800

Text #18

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.3735. Min Act: -0.0000

Data Index: 850702 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1855696 (The Pile)

Max Activating Token Index: 217