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

Dataset: The Pile

Neuron 915 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1817162 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.4533. Min Act: -0.0000

Data Index: 342677 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.4332. Min Act: -0.0000

Data Index: 570908 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1599501 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1265652 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1738960 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1032975 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1958840 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1338411 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3612. Min Act: -0.0000

Data Index: 984026 (The Pile)

Max Activating Token Index: 783

Text #10

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1736122 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3825. Min Act: -0.0000

Data Index: 871572 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1095022 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3602. Min Act: -0.0000

Data Index: 392035 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1180254 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3809. Min Act: -0.0000

Data Index: 222835 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3573. Min Act: -0.0000

Data Index: 787668 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3390. Min Act: -0.0000

Data Index: 481811 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1811141 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3456. Min Act: -0.0000

Data Index: 514541 (The Pile)

Max Activating Token Index: 234