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

Dataset: The Pile

Neuron 3073 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: 0.5716. Min Range: -0.5716

Max Act: 0.5716. Min Act: -0.0000

Data Index: 749948 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.5299. Min Act: -0.0000

Data Index: 9920 (The Pile)

Max Activating Token Index: 761

Text #2

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1904131 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4710. Min Act: -0.0000

Data Index: 56022 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4523. Min Act: -0.0000

Data Index: 940274 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4848. Min Act: -0.0000

Data Index: 456677 (The Pile)

Max Activating Token Index: 348

Text #6

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1315993 (The Pile)

Max Activating Token Index: 476

Text #7

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1691649 (The Pile)

Max Activating Token Index: 472

Text #8

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1940465 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1304203 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1771372 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4167. Min Act: -0.0000

Data Index: 294049 (The Pile)

Max Activating Token Index: 728

Text #12

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4650. Min Act: 0.0000

Data Index: 278640 (The Pile)

Max Activating Token Index: 267

Text #13

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1434090 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1260722 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4323. Min Act: -0.0000

Data Index: 573985 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1010096 (The Pile)

Max Activating Token Index: 733

Text #17

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1662929 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4444. Min Act: -0.0000

Data Index: 223022 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 0.5716. Min Range: -0.5716

Max Act: 0.4388. Min Act: -0.0000

Data Index: 465313 (The Pile)

Max Activating Token Index: 321