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

Dataset: The Pile

Neuron 3622 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: 3.8503. Min Range: -3.8503

Max Act: 3.8503. Min Act: -0.0000

Data Index: 1486971 (The Pile)

Max Activating Token Index: 17

Text #1

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.7415. Min Act: -0.0000

Data Index: 1795437 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.5810. Min Act: -0.0000

Data Index: 442721 (The Pile)

Max Activating Token Index: 467

Text #3

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.5615. Min Act: -0.0000

Data Index: 126781 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.4760. Min Act: -0.0000

Data Index: 1528513 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.5563. Min Act: -0.0000

Data Index: 209529 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.3949. Min Act: -0.0000

Data Index: 598146 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.3838. Min Act: -0.0000

Data Index: 847324 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.2248. Min Act: -0.0000

Data Index: 154215 (The Pile)

Max Activating Token Index: 605

Text #9

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.3431. Min Act: -0.0000

Data Index: 393850 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.1597. Min Act: -0.0000

Data Index: 1570508 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.9846. Min Act: -0.0000

Data Index: 1107560 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.1215. Min Act: -0.0000

Data Index: 1329258 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.9550. Min Act: -0.0000

Data Index: 1058160 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.0822. Min Act: -0.0000

Data Index: 1624661 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.0611. Min Act: -0.0000

Data Index: 1810699 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.2716. Min Act: -0.0000

Data Index: 700306 (The Pile)

Max Activating Token Index: 815

Text #17

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.1272. Min Act: -0.0000

Data Index: 1915559 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.9585. Min Act: -0.0000

Data Index: 1288907 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.9259. Min Act: -0.0000

Data Index: 1587941 (The Pile)

Max Activating Token Index: 75