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

Dataset: The Pile

Neuron 2273 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: 1.1639. Min Range: -1.1639

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1467176 (The Pile)

Max Activating Token Index: 240

Text #1

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0017. Min Act: -0.0000

Data Index: 425374 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9286. Min Act: -0.0000

Data Index: 214401 (The Pile)

Max Activating Token Index: 342

Text #3

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8631. Min Act: -0.0000

Data Index: 74070 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1970213 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1717852 (The Pile)

Max Activating Token Index: 608

Text #6

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8690. Min Act: -0.0000

Data Index: 872576 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8708. Min Act: -0.0000

Data Index: 857201 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8688. Min Act: -0.0000

Data Index: 938058 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8457. Min Act: -0.0000

Data Index: 86608 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1025191 (The Pile)

Max Activating Token Index: 484

Text #11

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8537. Min Act: -0.0000

Data Index: 414910 (The Pile)

Max Activating Token Index: 335

Text #12

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1196475 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.7877. Min Act: -0.0000

Data Index: 790050 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8550. Min Act: -0.0000

Data Index: 920804 (The Pile)

Max Activating Token Index: 196

Text #15

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1539532 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1904211 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1943459 (The Pile)

Max Activating Token Index: 184

Text #18

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.7842. Min Act: -0.0000

Data Index: 735902 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8056. Min Act: -0.0000

Data Index: 763104 (The Pile)

Max Activating Token Index: 300