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

Dataset: The Pile

Neuron 149 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.6231. Min Act: -0.0000

Data Index: 1675590 (The Pile)

Max Activating Token Index: 803

Text #1

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.5784. Min Act: -0.0000

Data Index: 847178 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.5393. Min Act: -0.0000

Data Index: 1427793 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.3553. Min Act: -0.0000

Data Index: 55669 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.2122. Min Act: -0.0000

Data Index: 1245706 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.4385. Min Act: -0.0000

Data Index: 1553385 (The Pile)

Max Activating Token Index: 1012

Text #6

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.4064. Min Act: -0.0000

Data Index: 1665614 (The Pile)

Max Activating Token Index: 243

Text #7

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.5304. Min Act: -0.0000

Data Index: 88162 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1085423 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.4339. Min Act: -0.0000

Data Index: 14801 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.4047. Min Act: -0.0000

Data Index: 1366092 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.5423. Min Act: -0.0000

Data Index: 1462242 (The Pile)

Max Activating Token Index: 823

Text #12

Max Range: 1.6231. Min Range: -1.6231

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1639201 (The Pile)

Max Activating Token Index: 801

Text #13

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.2495. Min Act: -0.0000

Data Index: 66190 (The Pile)

Max Activating Token Index: 283

Text #14

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.1294. Min Act: -0.0000

Data Index: 1939608 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1520270 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.1759. Min Act: -0.0000

Data Index: 688894 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.2363. Min Act: -0.0000

Data Index: 1110698 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.2439. Min Act: -0.0000

Data Index: 606240 (The Pile)

Max Activating Token Index: 791

Text #19

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.2126. Min Act: -0.0000

Data Index: 719741 (The Pile)

Max Activating Token Index: 1006