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

Dataset: The Pile

Neuron 1099 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: 3.9381. Min Range: -3.9381

Max Act: 3.9381. Min Act: -0.0000

Data Index: 1373402 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7487. Min Act: -0.0000

Data Index: 1777142 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5571. Min Act: -0.0000

Data Index: 480244 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5142. Min Act: -0.0000

Data Index: 1168863 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5498. Min Act: -0.0000

Data Index: 899678 (The Pile)

Max Activating Token Index: 275

Text #5

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5429. Min Act: -0.0000

Data Index: 69993 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5326. Min Act: -0.0000

Data Index: 1652288 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.4987. Min Act: -0.0000

Data Index: 119100 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.3058. Min Act: -0.0000

Data Index: 1648922 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.4219. Min Act: -0.0000

Data Index: 59390 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 3.9381. Min Range: -3.9381

Max Act: 2.9773. Min Act: -0.0000

Data Index: 324332 (The Pile)

Max Activating Token Index: 854

Text #11

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.3702. Min Act: -0.0000

Data Index: 1511954 (The Pile)

Max Activating Token Index: 468

Text #12

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.3700. Min Act: -0.0000

Data Index: 771748 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.2236. Min Act: -0.0000

Data Index: 1695955 (The Pile)

Max Activating Token Index: 711

Text #14

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5184. Min Act: -0.0000

Data Index: 744210 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.0822. Min Act: -0.0000

Data Index: 490758 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.4318. Min Act: -0.0000

Data Index: 576607 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7383. Min Act: -0.0000

Data Index: 748621 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.1766. Min Act: -0.0000

Data Index: 1341729 (The Pile)

Max Activating Token Index: 384

Text #19

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.4311. Min Act: -0.0000

Data Index: 1192567 (The Pile)

Max Activating Token Index: 77